
Sign up to save your podcasts
Or


Explore the full engineering blog here: https://medium.com/airbnb-engineering/improving-search-ranking-for-maps-13b03f2c2cca
This blog details how Airbnb improved its map search ranking algorithm. Initially, the algorithm prioritized listings based on booking probability, a method effective for list-based results but insufficient for map displays. Subsequent iterations modeled user attention on maps, first assuming uniform attention and then incorporating tiered attention and discounted attention based on pin location. These improvements, validated through A/B testing, led to significant increases in bookings and user satisfaction. Future work will focus on representing all available listings effectively on the map.
Explore the full engineering blog here: - https://netflixtechblog.com/title-launch-observability-at-netflix-scale-19ea916be1ed
Part 2 of a series on Netflix's title launch observability, focuses on practical solutions to ensure seamless title launches and discoverability. It emphasizes a strategic approach prioritizing understanding the interconnected stakeholders (launch operators, engineers, product managers, and creative representatives) and the core problem—fair treatment of titles by personalization systems. The authors introduce the "Title Health" concept for improved communication and monitoring, categorize issues (setup, personalization systems, algorithms), and analyze issue frequency and resolution effort. Finally, they detail their decision to prioritize proactive issue detection for maximum impact, laying the groundwork for future scalability.
Explore the full engineering blog here: https://www.linkedin.com/pulse/beyond-gpu-power-compute-roi-flywheel-jitendra-agarwal-a2ezc/
This blog post by a Netflix ML platform lead discusses maximizing the return on investment (ROI) of GPUs used in AI. It explains the crucial role of GPUs in AI workflows, including model training, fine-tuning, and inference, while highlighting the challenges of managing GPU resources effectively. The author introduces a "Compute ROI Flywheel" framework with five stages—investment, optimization, performance tuning, developer productivity, and minimizing idle resources—to improve GPU utilization. Practical tips are provided to optimize GPU compute across the AI lifecycle, emphasizing the importance of benchmarking, tracking utilization, right-sizing jobs, tuning workflows, and planning for capacity. Ultimately, the post advocates for a holistic approach to GPU management to achieve substantial ROI and enhance AI capabilities.
Explore the full engineering blog here: https://www.linkedin.com/blog/engineering/ai/practical-text-to-sql-for-data-analytics
This podcast script describes LinkedIn's SQL Bot, an AI assistant that translates natural language into SQL queries. The bot addresses the common problem of data analysts being overwhelmed with requests, by automating query generation and improving data accessibility. It uses embedding-based retrieval to find relevant tables and large language models to write and refine accurate SQL. Further, SQL Bot incorporates user feedback and offers a user-friendly interface with features like a "Fix with AI" button.The podcast highlights the bot's development, functionality, and future potential for enhanced data democratization within LinkedIn.
Explore the full engineering blog here: Netflix Tech Blog – Title Launch Observability
Netflix engineers face the challenge of monitoring thousands of monthly content launches. Initially relying on manual checks, they explored two automated solutions: log processing and dedicated observability endpoints within their personalization systems. Log processing proved insufficient for proactive issue detection and precise data, while observability endpoints offered real-time monitoring and enhanced accuracy, despite requiring significant upfront investment. The authors ultimately advocate for the observability endpoint approach to ensure successful title launches and enhance the viewer experience. A subsequent part will detail their implementation.