DataTalks.Club

In this episode Revathy Ramalingam, Senior Software Engineer and AI Engineer at a healthcare startup, shares her inspiring personal journey from over nine years in telecom software architecture to successfully transitioning back into the industry after a seven-year career break. We explore the evolution of the AI engineer role, the practical application of RAG pipelines, and the strategic use of AI tools to rebuild a technical career.

You'll learn about:

- AI Career Mapping: Using LLMs to design an upskilling roadmap.

- Vibe Coding: Leveraging AI tools for rapid prototyping.

- RAG Implementation: Building retrieval systems with LangChain.

- Interview Strategy: Proving technical skills after a career gap.

- Learning in Public: Building a network through community projects.

TIMECODES:

00:00 Why Move to AI? Using ChatGPT to Plan a Career Pivot

11:00 Learning in Public: The Power of Community Support

15:35 Telecom Capstone: Predicting Network Slices with ML

22:15 "Vibe Coding" & Building Prototypes with AI Dev Tools

28:00 The Interview Process: Navigating a 7-Year Career Break

33:45 Practical Interview Tasks: Building a PDF Q&A Assistant

39:40 Career Advice: Clear Plans, AI Mentors, and Hard Work

44:30 Closing Thoughts: Scaling the Learning Ladder

This talk is for developers and career-changers looking for a blueprint to enter the AI engineering space. It is ideal for those interested in RAG, healthcare tech, and practical career resets.

Connect with Revathy

- Github - https://github.com/RevathyRamalingam

- Linkedin - https://www.linkedin.com/in/revathy-ramalingam/

Connect with DataTalks.Club:

- Join the community - https://datatalks.club/slack.html

- Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ

- Check other upcoming events - https://lu.ma/dtc-events

- GitHub: https://github.com/DataTalksClub

- LinkedIn - https://www.linkedin.com/company/datatalks-club/

- Twitter - https://twitter.com/DataTalksClub

- Website - https://datatalks.club/

In this talk, Aditya, an experienced AI Researcher and Engineer, shares his technical evolution—from his roots in embedded systems to building complex, large-scale AI agent architectures. We explore the practical challenges of enterprise AI adoption, the shifting economics of LLMs, and the infrastructure required to deploy reliable multi-agent systems.You’ll learn about:- The ROI of Fine-Tuning: How to decide between specialized small models and general-purpose APIs based on cost and latency.- Agent MLOps Stack: The essential roles of guardrails, data lineage, and auditability in AI workflows.- Reliability in High-Stakes Verticals: Navigating the unique AI deployment challenges in the legal and healthcare sectors.- Evaluation Frameworks: How to design robust evals for multi-tenancy systems at scale.- Human-in-the-Loop: Strategies for aligning "LLM as a judge" with human-labeled ground truth to eliminate bias.- The Future of AGI: What to expect from the next wave of multimodal agents and autonomous systems.TIMECODES: 00:00 Aditya’s from embedded systems to AI08:52 Enterprise AI research and adoption gaps 13:13 AI reliability in legal and healthcare 19:16 Specialized models and agent governance 24:58 LLM economics: Fine-tuning vs. API ROI 30:26 Agent MLOps: Guardrails and data lineage 36:55 Iterating on agents with user feedback 43:30 AI evals for multi-tenancy and scale 50:18 Aligning LLM judges with human labels 56:40 Agent infrastructure and deployment risks 1:02:35 Future of AGI and multimodal agentsThis talk is designed for Machine Learning Engineers, Data Scientists, and Technical Product Managers who are moving beyond AI prototypes and into production-grade agentic workflows. It is especially relevant for those working in regulated industries or managing high-volume API budgets.Connect with Aditya:- Linkedin - https://www.linkedin.com/in/aditya-gautam-68233a30/Connect with DataTalks.Club:- Join the community - https://datatalks.club/slack.html- Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ- Check other upcoming events - https://lu.ma/dtc-events- GitHub: https://github.com/DataTalksClub- LinkedIn - https://www.linkedin.com/company/datatalks-club/ - Twitter - https://twitter.com/DataTalksClub - Website - https://datatalks.club/

In this talk, Juan, Analytics Engineer and author of Fundamentals of Analytics Engineering share his professional journey from studying psychological research in Colombia to becoming one of the first analytics engineers in the Netherlands. We explore the evolution of the role, the shift toward engineering rigor in data modeling, and how the landscape of tools like dbt and Databricks is changing the way teams work.

You’ll learn about:

• The fundamental differences between traditional BI engineering and modern analytics engineering.
• How to bridge the gap between business stakeholders and technical data infrastructure.
• The technical "glue" that connects Python and SQL for robust data pipelines.
• The importance of automated testing (generic vs. singular tests) to prevent "silent" data failures.
• Strategies for modeling messy, fragmented source data into a unified "business reality."
• The current state of the "Lakehouse" paradigm and how it impacts storage and compute costs.
• Expert advice on navigating the dbt ecosystem and its emerging competitors.

Links:

• DE Course: https://github.com/DataTalksClub/data-engineering-zoomcamp
• Luma: https://luma.com/0uf7mmup

TIMECODES:

0:00 Juan’s psychological research and transition to data

4:36 Riding the wave: The early days of analytics engineering

7:56 Breaking down the gap between analysts and engineers

11:03 The art of turning business reality into clean data

16:25 Why data engineering is about safety, not just speed

20:53 Reimagining data modeling in the modern era

26:53 To split or not to split: Finding the right team roles

30:35 Python, SQL, and the technical toolkit for success

38:41 How to stop manually testing your data dashboards

46:34 Bringing software engineering rigor to data workflows

49:50 Must-read books and resources for mastering the craft

55:42 The future of dbt and the shifting tool landscape

1:00:29 Deciphering the lakehouse: Warehousing in the cloud

1:11:16 Pro-tips for starting your data engineering journey

1:14:40 The big debate: Databricks vs. Snowflake

1:18:28 Why every data professional needs a local community

This talk is designed for data analysts looking to level up their engineering skills, data engineers interested in the business-logic layer, and data leaders trying to structure their teams more effectively. It is particularly valuable for those preparing for the Data Engineering Zoomcamp or anyone looking to transition into an Analytics Engineering role.

Connect with Juan

• Linkedin - https://www.linkedin.com/in/jmperafan/
• Website - https://juanalytics.com/

Connect with DataTalks.Club:

• Join the community - https://datatalks.club/slack.html
• Subscribe to our Google calendar to have all our events in your calendar
• https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ- Check other upcoming events
• https://lu.ma/dtc-events- GitHub: https://github.com/DataTalksClub
• LinkedIn - https://www.linkedin.com/company/datatalks-club/
• Twitter - https://twitter.com/DataTalksClub
• Website - https://datatalks.club/

In this episode of DataTalks.Club, Paul Iusztin, founding AI engineer and author of the LLM Engineer’s Handbook, breaks down the transition from traditional software development to production-grade AI engineering.

We explore the essential skill stack for 2026, the shift from "PoC purgatory" to shipping real products, and why the future of the field belongs to the full-stack generalist.

You’ll learn about:

- Why the role is evolving into the "new software engineer" and how to own the full product lifecycle.

- Identifying when to use traditional ML (like XGBoost) over LLMs to avoid over-engineering.

- The architectural shift from fine-tuning to mastering data pipelines and semantic search.

- Reliable Agentic Workflows- How to use coding assistants like Claude and Cursor to act as an architect rather than just a coder.

- Why human-in-the-loop evaluation is the most critical bottleneck in shipping reliable AI.

- How to build a "Second Brain" portfolio project that proves your end-to-end engineering value.

Links:

- Course link: https: https://academy.towardsai.net/courses/agent-engineering?ref=b3ab31

- Decoding AI Magazine: https://www.decodingai.com/

TIMECODES:

00:00 From code to cars: Paul’s journey to AI

07:08 Deep learning and the autonomous driving challenge

12:09 The transition to global product engineering

15:13 Survival guide: Data science vs. AI engineering

22:29 The full-stack AI engineer skill stack

29:12 Mastering RAG and knowledge management

32:27 The generalist edge: Learning with AI

42:21 Technical pillars for shipping AI products

54:05 Portfolio secrets and the "second brain"

58:01 The future of the LLM engineer’s handbook

This talk is designed for software engineers, data scientists, and ML engineers looking to move beyond proof-of-concepts and master the engineering rigors of shipping AI products in a production environment.

It is particularly valuable for those aiming for founding or lead AI roles in startups.

Connect with Paul

- Linkedin - https://www.linkedin.com/in/pauliusztin/

- Website - https://www.pauliusztin.ai/

Connect with DataTalks.Club:

- Join the community - https://datatalks.club/slack.html

- Subscribe to our Google calendar to have all our events in your calendar

- https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ

- Check other upcoming events - https://lu.ma/dtc-events

- GitHub: https://github.com/DataTalksClub

- LinkedIn - https://www.linkedin.com/company/datatalks-club/

- Twitter - https://twitter.com/DataTalksClub

- Website - https://datatalks.club/

In this talk, Rileen, a Senior Computational Biologist and Cancer Data Scientist, shares his professional journey from physics and computer science to cutting-edge cancer genomics and applied machine learning. From his early work in alternative splicing models to deep learning in medical imaging, Rileen explains how biology, data science, and AI intersect to transform cancer research.

TIMECODES:00:00 Rileen's Career Journey and Education06:14 Understanding Alternative Splicing in Computational Biology10:56 Modeling Alternative Splicing with Machine Learning14:52 Model Error Analysis and Transition to Cancer Research18:37 What Is Cancer? Mutational Theory Explained21:45 Cancer Treatments and Causes24:57 Cancer Genomics and Tumor Models28:59 Comparing Cell Lines and Tumor Samples (Multi-omics Analysis)32:32 Machine Learning Applications in Cancer Research35:38 Deep Learning for Medical Imaging and Pathology39:17 Data Privacy and Applied ML Course Projects42:50 Learning Outcomes and Future Plans46:36 Industry Experience in Pharmaceutical Research50:14 Day in the Life of a Computational Biologist55:02 Advice for Current ML Students58:40 Project Management and Challenges in Genomics1:02:23 Public Data Sets and Cancer Research in GermanyConnect with Rileen:- Twitter - https://x.com/RileenSinha- Linkedin - https://www.linkedin.com/in/rileen-sinha-a644692/- Github - https://github.com/OptimistixConnect with DataTalks.Club:- Join the community - https://datatalks.club/slack.html- Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ- Check other upcoming events - https://lu.ma/dtc-events- GitHub: https://github.com/DataTalksClub- LinkedIn - https://www.linkedin.com/company/datatalks-club/ - Twitter - https://twitter.com/DataTalksClub - Website - https://datatalks.club/

In this session Sofya shares her journey building a pet-tech startup that blends machine learning sensor data and canine behavior analytics. She walks through her path from early programming explorations to launching a health monitoring device designed around anomaly detection and long-term behavioral baselines.

TIMECODES:

00:00 Sofya's pet tech startup with machine learning sensor data and behavior pattern analytics

10:00 Journey from programming hobby to full time software development career

17:20 Career growth after skipping university and building practical experience

24:07 Puppy adoption story and family influence on pet focused innovation

32:16 Dog health monitoring framed as anomaly detection in real world machine learning

37:05 Collecting canine data with emphasis on sleep patterns and cycle tracking

43:35 Establishing a dogs normal baseline through long term data observation

49:34 Startup funding through personal savings and early stage bootstrapping

55:28 Finding cofounders and collaborators through meetups and coworking communities

59:48 Closing insights on Sofya's educational path and early device prototypes

Connect with Sofya

- Website - https://www.fit-tails.com/

- Linkedin - https://www.linkedin.com/in/sofya-yulpatova/

Connect with DataTalks.Club:

- Join the community - https://datatalks.club/slack.html

- Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ

- Check other upcoming events - https://lu.ma/dtc-events

- GitHub: https://github.com/DataTalksClub

- LinkedIn - https://www.linkedin.com/company/datatalks-club/

- Twitter - https://twitter.com/DataTalksClub

- Website - https://datatalks.club/

In this talk, Xia He-Bleinagel, Head of Data & Cloud at NOW GmbH, shares her remarkable journey from studying automotive engineering across Europe to leading modern data, cloud, and engineering teams in Germany.

We dive into her transition from hands-on engineering to leadership, how she balanced family with career growth, and what it really takes to succeed in today’s cloud, data, and AI job market.

TIMECODES:

00:00 Studying Automotive Engineering Across Europe

08:15 How Andrew Ng Sparked a Machine Learning Journey

11:45 Import–Export Work as an Unexpected Career Boos

t17:05 Balancing Family Life with Data Engineering Studies

20:50 From Data Engineer to Head of Data & Cloud

27:46 Building Data Teams & Tackling Tech Debt

30:56 Learning Leadership Through Coaching & Observation

34:17 Management vs. IC: Finding Your Best Fit

38:52 Boosting Developer Productivity with AI Tools

42:47 Succeeding in Germany’s Competitive Data Job Market

46:03 Fast-Track Your Cloud & Data Career

50:03 Mentorship & Supporting Working Moms in Tech

53:03 Cultural & Economic Factors Shaping Women’s Careers

57:13 Top Networking Groups for Women in Data

1:00:13 Turning Domain Expertise into a Data Career Advantage

Connect with Xia- Linkedin - https://www.linkedin.com/in/xia-he-bleinagel-51773585/

- Github - https://github.com/Data-Think-2021

- Website - https://datathinker.de/

Connect with DataTalks.Club:

- Join the community - https://datatalks.club/slack.html

- Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ

- Check other upcoming events - https://lu.ma/dtc-events

- GitHub: https://github.com/DataTalksClub

- LinkedIn - https://www.linkedin.com/company/datatalks-club/

- Twitter - https://twitter.com/DataTalksClub - Website - https://datatalks.club/

In this talk, Anusha Akkina, co-founder of Auralytix, shares her journey from working as a Chartered Accountant and Auditor at Deloitte to building an AI-powered finance intelligence platform designed to augment, not replace, human decision-making. Together with host Alexey from DataTalks.Club, she explores how AI is transforming finance operations beyond spreadsheets—from tackling ERP limitations to creating real-time insights that drive strategic business outcomes.

TIMECODES:

00:00 Building trust in AI finance and introducing Auralytix

02:22 From accounting roots to auditing at Deloitte and Paraxel

08:20 Moving to Germany and pivoting into corporate finance

11:50 The data struggle in strategic finance and the need for change

13:23 How Auralytix was born: bridging AI and financial compliance

17:15 Why ERP systems fail finance teams and how spreadsheets fill the gap

24:31 The real cost of ERP rigidity and lessons from failed transformations

29:10 The hidden risks of spreadsheet dependency and knowledge loss

37:30 Experimenting with ChatGPT and coding the first AI finance prototype

43:34 Identifying finance’s biggest pain points through user research

47:24 Empowering finance teams with AI-driven, real-time decision insights

50:59 Developing an entrepreneurial mindset through strategy and learning

54:31 Essential resources and finding the right AI co-founder

Connect with Anusha

- Linkedin - https://www.linkedin.com/in/anusha-akkina-acma-cgma-56154547/

- Website - https://aurelytix.com/

Connect with DataTalks.Club:

- Join the community - https://datatalks.club/slack.html

- Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ

- Check other upcoming events - https://lu.ma/dtc-events

- GitHub: https://github.com/DataTalksClub

- LinkedIn - https://www.linkedin.com/company/datatalks-club/

- Twitter - https://twitter.com/DataTalksClub

- Website - https://datatalks.club/

At Qdrant Conference, builders, researchers, and industry practitioners shared how vector search, retrieval infrastructure, and LLM-driven workflows are evolving across developer tooling, AI platforms, analytics teams, and modern search research.

Andrey Vasnetsov (Qdrant) explained how Qdrant was born from the need to combine database-style querying with vector similarity search—something he first built during the COVID lockdowns. He highlighted how vector search has shifted from an ML specialty to a standard developer tool and why hosting an in-person conference matters for gathering honest, real-time feedback from the growing community.

Slava Dubrov (HubSpot) described how his team uses Qdrant to power AI Signals, a platform for embeddings, similarity search, and contextual recommendations that support HubSpot’s AI agents. He shared practical use cases like look-alike company search, reflected on evaluating agentic frameworks, and offered career advice for engineers moving toward technical leadership.

Marina Ariamnova (SumUp) presented her internally built LLM analytics assistant that turns natural-language questions into SQL, executes queries, and returns clean summaries—cutting request times from days to minutes. She discussed balancing analytics and engineering work, learning through real projects, and how LLM tools help analysts scale routine workflows without replacing human expertise.

Evgeniya (Jenny) Sukhodolskaya (Qdrant) discussed the multi-disciplinary nature of DevRel and her focus on retrieval research. She shared her work on sparse neural retrieval, relevance feedback, and hybrid search models that blend lexical precision with semantic understanding—contributing methods like Mini-COIL and shaping Qdrant’s search quality roadmap through end-to-end experimentation and community education.

Speakers

Andrey Vasnetsov

Co-founder & CTO of Qdrant, leading the engineering and platform vision behind a developer-focused vector database and vector-native infrastructure.

Connect: https://www.linkedin.com/in/andrey-vasnetsov-75268897/

Slava Dubrov

Technical Lead at HubSpot working on AI Signals—embedding models, similarity search, and context systems for AI agents.

Connect: https://www.linkedin.com/in/slavadubrov/

Marina Ariamnova

Data Lead at SumUp, managing analytics and financial data workflows while prototyping LLM tools that automate routine analysis.

Connect: https://www.linkedin.com/in/marina-ariamnova/

Evgeniya (Jenny) Sukhodolskaya

Developer Relations Engineer at Qdrant specializing in retrieval research, sparse neural methods, and educational ML content.

Connect: https://www.linkedin.com/in/evgeniya-sukhodolskaya/

In this talk, Hugo Bowne-Anderson, an independent data and AI consultant, educator, and host of the podcasts Vanishing Gradients and High Signal, shares his journey from academic research and curriculum design at DataCamp to advising teams at Netflix, Meta, and the US Air Force. Together, we explore how to build reliable, production-ready AI systems—from prompt evaluation and dataset design to embedding agents into everyday workflows.

You’ll learn about:

• How to structure teams and incentives for successful AI adoption
• Practical prompting techniques for accurate timestamp and data generation
• Building and maintaining evaluation sets to avoid “prompt overfitting”- Cost-effective methods for LLM evaluation and monitoring
• Tools and frameworks for debugging and observing AI behavior (Logfire, Braintrust, Phoenix Arise)
• The evolution of AI agents—from simple RAG systems to proactive, embedded assistants
• How to escape “proof of concept purgatory” and prioritize AI projects that drive business value
• Step-by-step guidance for building reliable, evaluable AI agents

This session is ideal for AI engineers, data scientists, ML product managers, and startup founders looking to move beyond experimentation into robust, scalable AI systems. Whether you’re optimizing RAG pipelines, evaluating prompts, or embedding AI into products, this talk offers actionable frameworks to guide you from concept to production.

LINKS

• Escaping POC Purgatory: Evaluation-Driven Development for AI Systems - https://www.oreilly.com/radar/escaping-poc-purgatory-evaluation-driven-development-for-ai-systems/
• Stop Building AI Agents - https://www.decodingai.com/p/stop-building-ai-agents
• How to Evaluate LLM Apps Before You Launch - https://www.youtube.com/watch?si=90fXJJQThSwGCaYv&v=TTr7zPLoTJI&feature=youtu.be
• My Vanishing Gradients Substack - https://hugobowne.substack.com/
• Building LLM Applications for Data Scientists and Software Engineers
• https://maven.com/hugo-stefan/building-ai-apps-ds-and-swe-from-first-principles?promoCode=datatalksclub

TIMECODES:

00:00 Introduction and Expertise

04:04 Transition to Freelance Consulting and Advising

08:49 Restructuring Teams and Incentivizing AI Adoption

12:22 Improving Prompting for Timestamp Generation

17:38 Evaluation Sets and Failure Analysis for Reliable Software

23:00 Evaluating Prompts: The Cost and Size of Gold Test Sets

27:38 Software Tools for Evaluation and Monitoring

33:14 Evolution of AI Tools: Proactivity and Embedded Agents

40:12 The Future of AI is Not Just Chat

44:38 Avoiding Proof of Concept Purgatory: Prioritizing RAG for Business Value

50:19 RAG vs. Agents: Complexity and Power Trade-Offs

56:21 Recommended Steps for Building Agents

59:57 Defining Memory in Multi-Turn Conversations

Connect with Hugo

• Twitter - https://x.com/hugobowne
• Linkedin - https://www.linkedin.com/in/hugo-bowne-anderson-045939a5/
• Github - https://github.com/hugobowne
• Website - https://hugobowne.github.io/

Connect with DataTalks.Club:

• Join the community - https://datatalks.club/slack.html
• Subscribe to our Google calendar to have all our events in your calendar - https://calendar.google.com/calendar/r?cid=ZjhxaWRqbnEwamhzY3A4ODA5azFlZ2hzNjBAZ3JvdXAuY2FsZW5kYXIuZ29vZ2xlLmNvbQ
• Check other upcoming events - https://lu.ma/dtc-events
• GitHub: https://github.com/DataTalksClub- LinkedIn - https://www.linkedin.com/company/datatalks-club/
• Twitter - https://twitter.com/DataTalksClub - Website - https://datatalks.club/