Agentic Conversations (formally mlops.community)

Databricks Roundtable episode: Operationalizing AI Agents: From Experimentation to Production.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps GPU Guide: https://go.mlops.community/gpuguide

Big shout-out to Databricks for the collaboration!

// Abstract

This panel discusses the real-world challenges of deploying AI agents at scale. The conversation explores technical and operational barriers that slow production adoption, including reliability, cost, governance, and security.

The panelists also examine how LLMOps, AIOps, and AgentOps differ from traditional MLOps, and why new approaches are required for generative and agent-based systems. Finally, experts define success criteria for GenAI frameworks, with a focus on robust evaluation, observability, and continuous monitoring across development and staging environments.

// Bio

Samraj Moorjani

Samraj is a software engineer working on the Agent Quality team. Previously, Samraj worked at Meta on ads/product classification research and AppLovin on MLOps. Samraj graduated with a BS+MS in Computer Science from UIUC, advised by Professor Hari Sundaram, where he worked on controllable natural language generation to produce appealing, interpretable science to combat the spread of misinformation. He also worked with Professor Wen-mei Hwu on accelerating LLM inference through extreme sparsification.

Apurva Misra

Apurva is an AI Consultant at Sentick, focusing on assisting startups with their AI strategy and building solutions. She leverages her extensive experience in machine learning and a Master's degree from the University of Waterloo, where her research bridged driving and machine learning, to offer valuable insights. Apurva's keen interest in the startup world fuels her passion for helping emerging companies incorporate AI effectively. In her free time, she is learning Spanish, and she also enjoys exploring hidden gem eateries, always eager to hear about new favourite spots!

Ben Epstein

Ben was the machine learning lead for Splice Machine, leading the development of their MLOps platform and Feature Store. He is now the Co-founder and CTO at GrottoAI, focused on supercharging multifamily teams and reducing vacancy loss with AI-powered guidance for leasing and renewals. Ben also works as an adjunct professor at Washington University in St. Louis, teaching concepts in cloud computing and big data analytics.

Hosted by Adam Becker

// Related Links

Website: https://www.databricks.com/https://mlflow.org/

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Samraj on LinkedIn: /samrajmoorjani/

Connect with Apurva on LinkedIn: /apurva-misra/

Connect with Ben on LinkedIn: /ben-epstein/

Connect with Adam on LinkedIn: /adamissimo/

Timestamps:

[00:00] Introduction

[02:30] AI Agents in Operations

[04:36] AI Strategy Consulting

[05:30] Agent Quality Focus

[06:17] AI Agent Expectations

[11:44] AI Use Cases Evolution

[15:25] Agent Expectations Adjustment

[17:41] Agent Quality Monitoring

[23:22] Trust in GenAI Systems

[33:33] Data Prep vs Product Thinking

[40:27] Quality Systems Distinction

[44:54] Q & A

[1:00:57] Wrap up

Lorenzo Moriondo is a Technical Lead for AI at tuned.org.uk, working on AI agent protocols, graph-based search, and production-grade LLM systems.

arrowspace: Vector Spaces and Graph Wiring // MLOps Podcast #365 with Lorenzo Moriondo, AI Research and Product Engineer

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps GPU Guide: https://go.mlops.community/gpuguide

// Abstract

Meet arrowspace — an open-source library for curating and understanding LLM datasets across the entire lifecycle, from pre-training to inference. Instead of treating embeddings as static vectors, arrowspace turns them into graphs (“graph wiring”) so you can explore structure, not just similarity. That unlocks smarter RAG search (beyond basic semantic matching), dataset fingerprinting, and deeper insights into how different datasets behave.

You can compare datasets, predict how changes will affect performance, detect drift early, and even safely mix data sources while measuring outcomes.

In short: arrowspace helps you see your data — and make better decisions because of it.

// Bio

With over a decade of experience in software and data engineering across startups and early-stage projects, Lorenzo has recently turned his focus to the AI-assisted movement to automate software and data operations. He has contributed to and founded projects within various open-source communities, including work with Summer of Code, where he focused on the Semantic Web and REST APIs.A strong enthusiast of Python and Rust, he develops tools centered around LLMs and agentic systems. He is a maintainer of the SmartCore ML library, as well as the creator of Arrowspace and the Topological Transformer.

// Related Links

Website: https://www.tuned.org.uk

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Chris on LinkedIn: /lorenzomoriondo

Timestamps:

[00:00] Graph Wiring for ML

[00:32] RAG and Vector Similarity

[08:58] Geometric Search Trade-offs

[13:12] Vector DB Algorithm Integration

[21:32] Feature-Based Retrieval Shift

[26:04] Epiplexity and Embeddings

[31:26] Epiplexity and Embedding Structure

[40:15] Training vs Post-hoc Models

[47:16] Discovery-Driven Development

[51:22] Updating Mental Models

[53:00] Vector Search vs Agents

[55:30] Wrap up

Donné Stevenson is a Machine Learning Engineer at Prosus, working on scalable ML infrastructure and productionizing GenAI systems across portfolio companies.

Pedro Chaves is a Data Science Manager at OLX Group, working on GenAI-powered search, personalization, and large-scale marketplace recommendations.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps GPU Guide: https://go.mlops.community/gpuguide

// Abstract

Marketplaces are about to get smarter.Agents that find your perfect house, negotiate the best deals, and even talk to other agents on your behalf.

Less tedious searching. Less back-and-forth. More time for what matters.

Pedro Chaves and Donné Stevenson discuss the future of buying and selling cars, homes, and everything in between - and what it'll take to get there.

// Bio

Donné Stevenson

Focused on building AI-powered products that give companies the tools and expertise needed to harness the power of AI in their respective fields.

Pedro Chaves

Pedro is a Data Science Manager at OLX Group, where he leads teams building machine learning solutions to improve marketplace performance, pricing, and user experience at scale.

// Related Links

Website: https://www.prosus.com/

Website: https://www.olxgroup.com/

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

MLOps GPU Guide: https://go.mlops.community/gpuguide

Timestamps:

[00:00] OLX: Disrupting Buyer-Seller Experiences

[03:33] Redefining the Home-Buying Experience

[07:40] User Feedback and Iterative Rollouts

[11:25] Beyond Chat: Redefining Agent Use

[14:03] User Trust and Education Challenges

[16:47] Learning Curve for Automoto

[20:05] Interactive Decision-Making with AI

[24:47] Agents Simplify Buyer-Seller Search

[28:14] Garage Sale Treasure Hunting

[33:43] Agent Discovery Layer Needed

[34:53] Agents Relying on Agents

[39:48] Reducing Friction in Selling Stuff

[41:39] Extracting Buyer Intent Systematically

[44:49] Optimizing Delivery with Lockers

[50:10] Generative AI Commerce Strategies

[51:03] Improving Chat Interaction Layer

Johann Schleier-Smith is the Technical Lead for AI at Temporal Technologies, working on reliable infrastructure for production AI systems and long-running agent workflows.

Durable Execution and Modern Distributed Systems, Johann Schleier-Smith // MLOps Podcast #364

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps Merch: https://shop.mlops.community/

Big shoutout to ⁨ @Temporalio  for the support, and to  @trychroma  for hosting us in their recording studio

// Abstract

A new paradigm is emerging for building applications that process large volumes of data, run for long periods of time, and interact with their environment. It’s called Durable Execution and is replacing traditional data pipelines with a more flexible approach. Durable Execution makes regular code reliable and scalable.

In the past, reliability and scalability have come from restricted programming models, like SQL or MapReduce, but with Durable Execution, this is no longer the case. We can now see data pipelines that include document processing workflows, deep research with LLMs, and other complex and LLM-driven agentic patterns expressed at scale with regular Python programs.

In this session, we describe Durable Execution and explain how it fits in with agents and LLMs to enable a new class of machine learning applications.

// Related Links

https://t.mp/hello?utm_source=podcast&utm_medium=sponsorship&utm_campaign=podcast-2026-03-13-mlops&utm_content=mlops-johann

https://t.mp/vibe?utm_source=podcast&utm_medium=sponsorship&utm_campaign=podcast-2026-03-13-mlops&utm_content=mlops-johann

https://t.mp/career?utm_source=podcast&utm_medium=sponsorship&utm_campaign=podcast-2026-03-13-mlops&utm_content=mlops-johann

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Johann on LinkedIn: /jssmith/

March 3rd, Computer History Museum CODING AGENTS CONFERENCE, come join us while there are still tickets left.

https://luma.com/codingagents

Chris Fregly is currently focused on building and scaling high-performance AI systems, writing and teaching about AI infrastructure, helping organizations adopt generative AI and performance engineering principles on AWS, and fostering large developer communities around these topics.

Performance Optimization and Software/Hardware Co-design across PyTorch, CUDA, and NVIDIA GPUs // MLOps Podcast #363 with Chris Fregly, Founder, AI Performance Engineer, and Investor

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps GPU Guide: https://go.mlops.community/gpuguide

// Abstract

In today’s era of massive generative models, it's important to understand the full scope of AI systems' performance engineering. This talk discusses the new O'Reilly book, AI Systems Performance Engineering, and the accompanying GitHub repo (https://github.com/cfregly/ai-performance-engineering).

This talk provides engineers, researchers, and developers with a set of actionable optimization strategies. You'll learn techniques to co-design and co-optimize hardware, software, and algorithms to build resilient, scalable, and cost-effective AI systems for both training and inference.

// Bio

Chris Fregly is an AI performance engineer and startup founder with experience at AWS, Databricks, and Netflix. He's the author of three (3) O'Reilly books, including Data Science on AWS (2021), Generative AI on AWS (2023), and AI Systems Performance Engineering (2025). He also runs the global AI Performance Engineering meetup and speaks at many AI-related conferences, including Nvidia GTC, ODSC, Big Data London, and more.

// Related Links

AI Systems Performance Engineering: Optimizing Model Training and Inference Workloads with GPUs, CUDA, and PyTorch 1st Edition by Chris Fregly: https://www.amazon.com/Systems-Performance-Engineering-Optimizing-Algorithms/dp/B0F47689K8/

Coding Agents Conference: https://luma.com/codingagents

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Chris on LinkedIn: /cfregly

Timestamps:

[00:00] SageMaker HyperPod Resilience

[00:27] Book Creation and Software Engineering

[04:57] Software Engineers and Maintenance

[11:49] AI Systems Performance Engineering

[22:03] Cognitive Biases and Optimization / "Mechanical Sympathy"

[29:36] GPU Rack-Scale Architecture

[33:58] Data Center Reliability Issues

[43:52] AI Compute Platforms

[49:05] Hardware vs Ecosystem Choice

[1:00:05] Claude vs Codex vs Gemini

[1:14:53] Kernel Budget Allocation

[1:18:49] Steerable Reasoning Challenges

[1:24:18] Data Chain Value Awareness

Roundtable CAST AI episode: Serving LLMs in Production: Performance, Cost & Scale.

Join the Community:

https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps GPU Guide:

https://go.mlops.community/gpuguide

// Abstract

Experimenting with LLMs is easy. Running them reliably and cost-effectively in production is where things break.

Most AI teams never make it past demos and proofs of concept. A smaller group is pushing real workloads to production—and running into very real challenges around infrastructure efficiency, runaway cloud costs, and reliability at scale.

This session is for engineers and platform teams moving beyond experimentation and building AI systems that actually hold up in production.

// Bio

Ioana Apetrei

Ioana is a Senior Product Manager at CAST AI, leading the AI Enabler product, an AI Gateway platform for cost-effective LLM infrastructure deployment. She brings 12 years of experience building B2C and B2B products reaching over 10 million users. Outside of work, she enjoys assembling puzzles and LEGOs and watching motorsports.

Igor Šušić

Igor is a founding Machine Learning Engineer at CAST AI’s AI Enabler, where he focuses on optimizing inference and training at scale. With a strong background in Natural Language Processing (NLP) and Recommender Systems, Igor has been tackling the challenges of large-scale model optimization long before transformers became mainstream. Prior to CAST AI, he worked at industry leaders like Bloomreach and Infobip, where he contributed to the development and deployment of large-scale AI and personalization systems from the early days of the field.

// Related Links

Website: https://cast.ai/

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Ioana on LinkedIn: /ioanaapetrei/

Connect with Igor on LinkedIn: /igor-%C5%A1u%C5%A1i%C4%87/

Rahul Raja is a Staff Software Engineer at LinkedIn, working on large-scale search infrastructure, information retrieval systems, and integrating AI/ML to improve ranking and semantic search experiences.

The Future of Information Retrieval: From Dense Vectors to Cognitive Search // MLOps Podcast #362 with Rahul Raja, Staff Software Engineer at LinkedIn

Join the Community:

https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps GPU Guide: https://go.mlops.community/gpuguide

// Abstract

Information Retrieval is evolving from keyword matching to intelligent, vector-based understanding. In this talk, Rahul Raja explores how dense retrieval, vector databases, and hybrid search systems are redefining how modern AI retrieves, ranks, and reasons over information. He discusses how retrieval now powers large language models through Retrieval-Augmented Generation (RAG) and the new MLOps challenges that arise, embedding drift, continuous evaluation, and large-scale vector maintenance.

Looking ahead, the session envisions a future of Cognitive Search, where retrieval systems move beyond recall to genuine reasoning, contextual understanding, and multimodal awareness. Listeners will gain insight into how the next generation of retrieval will bridge semantics, scalability, and intelligence, powering everything from search and recommendations to generative AI.

// BioRahul is a Staff Engineer at LinkedIn, where he focuses on search and deployment systems at scale. Rahul is a graduate from Carnegie Mellon University and has a strong background in building reliable, high-performance infrastructure. He has led many initiatives to improve search relevance and streamline ML deployment workflows.

// Related Links

Website: https://www.linkedin.com/

Coding Agents Conference: https://luma.com/codingagents

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Rahul on LinkedIn: /rahulraja963/

Timestamps:

[00:00] Vector Search for Media

[00:33] RAG and Search Evolution

[04:45] Cognitive vs Semantic Search

[08:26] High Value Search Signals

[16:43] Scaling with Embeddings

[22:37] BM25 Benchmark Bias

[29:00] Video Search Use Cases

[31:21] Context and Search Tradeoff

[35:04] Personal Memory Augmentation

[39:03] Future of Cognitive Search

[44:51] Access Control in Vectors

[49:14] Search Ranking Challenge

[54:43] Hard Search Problems Solved

[58:29] Freshness vs Cost

[1:02:12] Wrap up

Vincent Warmerdam is a Founding Engineer at marimo, working on reinventing Python notebooks as reactive, reproducible, interactive, and Git-friendly environments for data workflows and AI prototyping. He helps build the core marimo notebook platform, pushing its reactive execution model, UI interactivity, and integration with modern development and AI tooling so that notebooks behave like dependable, shareable programs and apps rather than error-prone scratchpads.

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps GPU Guide: https://go.mlops.community/gpuguide

// Abstract

Vincent Warmerdam joins Demetrios fresh off marimo’s acquisition by Weights & Biases—and makes a bold claim: notebooks as we know them are outdated.

They talk Molab (GPU-backed, cloud-hosted notebooks), LLMs that don’t just chat but actually fix your SQL and debug your code, and why most data folks are consuming tools instead of experimenting. Vincent argues we should stop treating notebooks like static scratchpads and start treating them like dynamic apps powered by AI.

It’s a conversation about rethinking workflows, reclaiming creativity, and not outsourcing your brain to the model.

// Bio

Vincent is a senior data professional who worked as an engineer, researcher, team lead, and educator in the past. You might know him from tech talks with an attempt to defend common sense over hype in the data space. He is especially interested in understanding algorithmic systems so that one may prevent failure. As such, he has always had a preference to keep calm and check the dataset before flowing tonnes of tensors. He currently works at marimo, where he spends his time rethinking everything related to Python notebooks.

// Related Links

Website: https://marimo.io/

Coding Agent Conference: https://luma.com/codingagents

Hyperbolic GPU Cloud: app.hyperbolic.ai

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

MLOps GPU Guide: https://go.mlops.community/gpuguide

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Vincent on LinkedIn: /vincentwarmerdam/

Timestamps:

[00:00] Context in Notebooks

[00:24] Acquisition and Team Continuity

[04:43] Coding Agent Conference Announcement!

[05:56] Hyperbolic GPU Cloud Ad

[06:54] marimo and W&B Synergies

[09:31] marimo Cloud Code Support

[12:59] Hardest Code to Generate

[16:22] Trough of Disillusionment

[20:38] Agent Interaction in Notebooks

[25:41] Wrap up

Ereli Eran is the Founding Engineer at 7AI, where he’s focused on building and scaling the company’s agentic AI-driven cybersecurity platform — developing autonomous AI agents that triage alerts, investigate threats, enrich security data, and enable end-to-end automated security operations so human teams can focus on higher-value strategic work.

Software Engineering in the Age of Coding Agents: Testing, Evals, and Shipping Safely at Scale // MLOps Podcast #361 with Ereli Eran, Founding Engineer at 7AI

Join the Community: https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps GPU Guide: https://go.mlops.community/gpuguide

// Abstract

A conversation on how AI coding agents are changing the way we build and operate production systems. We explore the practical boundaries between agentic and deterministic code, strategies for shared responsibility across models, engineering teams, and customers, and how to evaluate agent performance at scale. Topics include production quality gates, safety and cost tradeoffs, managing long-tail failures, and deployment patterns that let you ship agents with confidence.

// Bio

Ereli Eran is a founding engineer at 7AI, where he builds agentic AI systems for security operations and the production infrastructure that powers them. His work spans the full stack - from designing experiment frameworks for LLM-based alert investigation to architecting secure multi-tenant systems with proper authentication boundaries. Previously, he worked in data science and software engineering roles at Stripe, VMware Carbon Black, and was an early employee of Ravelin and Normalyze.

// Related Links

Website: https://7ai.com/

Coding Agents Conference: https://luma.com/codingagents

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Ereli on LinkedIn: /erelieran/

Timestamps:

[00:00] Language Sensitivity in Reasoning

[00:25] Value of Claude Code

[01:54] AI in Security Workflows

[06:21] Agentic Systems Failures

[12:50] Progressive Disclosure in Voice Agents

[16:39] LLM vs Classic ML

[19:44] Hybrid Approach to Fraud

[25:58] Debugging with User Feedback

[33:52] Prompts as Code

[42:07] LLM Security Workflow

[45:10] Shared Memory in Security

[49:11] Common Agent Failure Modes

[53:34] Wrap up

Nick Gillian is the Co-Founder and CTO at Archetype AI, working on physical AI foundation models that understand and reason over real-world sensor data.

Physical AI: Teaching Machines to Understand the Real World // MLOps Podcast #360 with Nick Gillian, Co-Founder and CTO of Archetype AI

Join the Community:

https://go.mlops.community/YTJoinIn

Get the newsletter: https://go.mlops.community/YTNewsletter

MLOps GPU Guide: https://go.mlops.community/gpuguide

/ Abstract

As AI moves beyond the cloud and simulation, the next frontier is Physical AI: systems that can perceive, understand, and act within real-world environments in real time. In this conversation, Nick Gillian, Co-Founder and CTO of Archetype AI, explores what it actually takes to turn raw sensor and video data into reliable, deployable intelligence.

Drawing on his experience building Google’s Soli and Jacquard and now leading development of Newton, a foundational model for Physical AI, Nick discusses how real-time physical understanding changes what’s possible across safety monitoring, infrastructure, and human–machine interaction. He’ll share lessons learned translating advanced research into products that operate safely in dynamic environments, and why many organizations underestimate the challenges and opportunities of AI in the physical world.

// Bio

Nick Gillian, Ph.D., is Co-Founder and CTO of Archetype AI with over 15 years of experience turning advanced AI and interaction research into real-world products. At Archetype, he leads the AI and engineering teams behind Newton—a first-of-its-kind Physical AI foundational model that can perceive, understand, and reason about the physical world. Before co-founding Archetype, Nick was a Senior Staff Machine Learning Engineer at Google and a researcher at MIT, where he developed AI and ML methods for real-time sensor understanding. At Google’s Advanced Technology and Projects group, he led machine learning research that powered breakthrough products like Soli radar and Jacquard, and helped advance sensing algorithms across Pixel, Nest, and wearable devices.

// Related Links

Website: https://www.archetypeai.io/https://www.archetypeai.io/blog/timefusion-newton https://www.nature.com/articles/s41598-023-44714-2https://www.youtube.com/watch?v=Pow4utY9teU https://www.youtube.com/watch?v=uE0jjdzwe9w https://arxiv.org/abs/2410.14724

Coding Agents Conference: https://luma.com/codingagents

~~~~~~~~ ✌️Connect With Us ✌️ ~~~~~~~

Catch all episodes, blogs, newsletters, and more: https://go.mlops.community/TYExplore

Join our Slack community [https://go.mlops.community/slack]

Follow us on X/Twitter [@mlopscommunity](https://x.com/mlopscommunity) or [LinkedIn](https://go.mlops.community/linkedin)]

Sign up for the next meetup: [https://go.mlops.community/register]

MLOps Swag/Merch: [https://shop.mlops.community/]

Connect with Demetrios on LinkedIn: /dpbrinkm

Connect with Nick on LinkedIn: /nick-gillian-b27b1094/

Timestamps:[00:00] Physical Agent Framework[00:56] Physical AI Clarification[06:53] Building a Repair Model[12:41] World Models and LLMs[17:17] Data Weighting Strategies[24:19] Data Diversity vs Quantity[38:30] R&D and Product Creation[41:22] Construction Site Data Shipping[50:33] Wrap up