The Curious Engineer

All blogs / AI / ML

Eugene Yan

eugeneyan.com

I work to bridge the field and the frontier, and help build safe, reliable AI systems that scale. I also write and speak about AI-powered systems and products, and prototype for fun.

AI / MLSoftware / engineering practiceEngineering management / careers

’15’16’17’18’19’20’21’22’23’24’25’26
Posts
212 from 20 Jun 2015 to 21 Jun 2026
Posting
now and then (5 in the last year)
Kind
personal blog
Feed
https://eugeneyan.com/rss/

2026 3

  1. Patterns for Building Cybersecurity Evals
  2. Using LLMs to Secure Source Code
  3. How to Work and Compound with AI

2025 13

  1. 2025 Year in Review
  2. Product Evals in Three Simple Steps
  3. Advice for New Principal Tech ICs (i.e., Notes to Myself)
  4. Training an LLM-RecSys Hybrid for Steerable Recs with Semantic IDs
  5. Evaluating Long-Context Question & Answer Systems
  6. AI Engineer 2025 - Improving RecSys & Search with LLM techniques
  7. Exceptional Leadership: Some Qualities, Behaviors, and Styles
  8. Building News Agents for Daily News Recaps with MCP, Q, and tmux
  9. An LLM-as-Judge Won't Save The Product—Fixing Your Process Will
  10. Frequently Asked Questions about My Writing Process
  11. NVIDIA GTC 2025 - Building LLM-Powered Applications
  12. Improving Recommendation Systems & Search in the Age of LLMs
  13. Building AI Reading Club: Features & Behind the Scenes

2024 19

  1. 2024 Year in Review
  2. Seemingly Paradoxical Rules of Writing
  3. How to Run a Weekly Paper Club (and Build a Learning Community)
  4. My Minimal MacBook Pro Setup Guide
  5. 39 Lessons on Building ML Systems, Scaling, Execution, and More
  6. AlignEval: Building an App to Make Evals Easy, Fun, and Automated
  7. Weights & Biases LLM-Evaluator Hackathon - Hackathon Judge
  8. Building the Same App Using Various Web Frameworks
  9. Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge)
  10. How to Interview and Hire ML/AI Engineers
  11. AI Engineer 2024 Keynote - What We Learned from a Year of LLMs
  12. Netflix PRS 2024 - Applying LLMs to Recommendation Experiences
  13. Prompting Fundamentals and How to Apply them Effectively
  14. What We've Learned From A Year of Building with LLMs
  15. Building an AI Coach to Help Tame My Monkey Mind
  16. Task-Specific LLM Evals that Do & Don't Work
  17. Don't Mock Machine Learning Models In Unit Tests
  18. How to Generate and Use Synthetic Data for Finetuning
  19. Language Modeling Reading List (to Start Your Paper Club)

2023 22

  1. 2023 Year in Review
  2. Push Notifications: What to Push, What Not to Push, and How Often
  3. Out-of-Domain Finetuning to Bootstrap Hallucination Detection
  4. Reflections on AI Engineer Summit 2023
  5. AI Engineer 2023 Keynote - Building Blocks for LLM Systems
  6. Evaluation & Hallucination Detection for Abstractive Summaries
  7. How to Match LLM Patterns to Problems
  8. Patterns for Building LLM-based Systems & Products
  9. Obsidian-Copilot: An Assistant for Writing & Reflecting
  10. Some Intuition on Attention and the Transformer
  11. Open-LLMs - A list of LLMs for Commercial Use
  12. Interacting with LLMs with Minimal Chat
  13. More Design Patterns For Machine Learning Systems
  14. Raspberry-LLM - Making My Raspberry Pico a Little Smarter
  15. Experimenting with LLMs to Research, Reflect, and Plan
  16. LLM-powered Biographies
  17. How to Write Data Labeling/Annotation Guidelines
  18. Content Moderation & Fraud Detection - Patterns in Industry
  19. Mechanisms for Effective Technical Teams
  20. Mechanisms for Effective Machine Learning Projects
  21. Goodbye Roam Research, Hello Obsidian
  22. What To Do If Dependency Teams Can’t Help

2022 19

  1. 2022 in Review & 2023 Goals
  2. Autoencoders and Diffusers: A Brief Comparison
  3. Text-to-Image: Diffusion, Text Conditioning, Guidance, Latent Space
  4. RecSys 2022: Recap, Favorite Papers, and Lessons
  5. RecSys 2022 Keynote - Is the Juice Worth the Squeeze?
  6. Writing Robust Tests for Data & Machine Learning Pipelines
  7. Simplicity is An Advantage but Sadly Complexity Sells Better
  8. Uncommon Uses of Python in Commonly Used Libraries
  9. Why You Should Write Weekly 15-5s
  10. Design Patterns in Machine Learning Code and Systems
  11. What I Wish I Knew About Onboarding Effectively
  12. Bandits for Recommender Systems
  13. How to Measure and Mitigate Position Bias
  14. Counterfactual Evaluation for Recommendation Systems
  15. Traversing High-Level Intent and Low-Level Requirements
  16. Data Science Project Quick-Start
  17. Mailbag: How to Define a Data Team's Vision and Roadmap
  18. Red Flags to Look Out for When Joining a Data Team
  19. How to Keep Learning about Machine Learning

2021 37

  1. The Data Scientist Show - Building end-to-end ML systems
  2. 2021 Year in Review
  3. Informal Mentors Grew into ApplyingML.com!
  4. 5 Lessons I Learned from Writing Online (Guest post by Susan Shu)
  5. What I Learned from Writing Online - For Fellow Non-Writers
  6. RecSys 2021 - Papers and Talks to Chew on
  7. The First Rule of Machine Learning: Start without Machine Learning
  8. MLOps Community - System Design for RecSys & Search
  9. Reinforcement Learning for Recommendations and Search
  10. Amazon Science - Eugene Yan and the Art of Writing about Science
  11. Bootstrapping Labels via ___ Supervision & Human-In-The-Loop
  12. Mailbag: How to Bootstrap Labels for Relevant Docs in Search
  13. SF Big Analytics - System Design for RecSys & Search
  14. Influencing without Authority for Data Scientists
  15. System Design for Recommendations and Search
  16. Patterns for Personalization in Recommendations and Search
  17. Towards Data Science - Author Spotlight with Eugene Yan
  18. The Metagame of Applying Machine Learning
  19. Search: Query Matching via Lexical, Graph, and Embedding Methods
  20. My Impostor Syndrome Stories (Guest Post by Susan Shu)
  21. How to Live with Chronic Imposter Syndrome
  22. Planning Your Career: Values and Superpowers
  23. Bukalapak - Fireside Chat with the Data Science team
  24. TalkPython - What ML can Teach Us About Life
  25. Choosing Problems in Data Science and Machine Learning
  26. Seven Habits that Shaped My Last Decade
  27. How to Write Design Docs for Machine Learning Systems
  28. How to Write Better with The Why, What, How Framework
  29. Feature Stores: A Hierarchy of Needs
  30. How to Win a Data Hackathon (Hacklytics 2021)
  31. DataTalksClub - Building an ML System; Behind the Scenes
  32. Growing and Running Your Data Science Team
  33. You Don't Really Need Another MOOC
  34. DataTalksClub - The Importance Of Writing In A Tech Career
  35. Mailbag: How to Get Experienced DS Resume Noticed by Recruiters?
  36. Real-time Machine Learning For Recommendations
  37. 2021 Roadmap: Sharing, Helping, and Living More

2020 59

  1. 2020 Retrospective: New Country, New Role, New Habit
  2. Catch the Flying Daggers
  3. How I’m Reflecting on 2020 and Planning for 2021
  4. Alexey Grigorev on His Career, Data Science, and Writing
  5. Mailbag: What's the Architecture for your Blog?
  6. What Machine Learning Can Teach Us About Life - 7 Lessons
  7. How to Prevent or Deal with a Data Science Role or Title Mismatch
  8. Applied / Research Scientist, ML Engineer: What’s the Difference?
  9. Chip Huyen on Her Career, Writing, and Machine Learning
  10. Data Discovery Platforms and Their Open Source Solutions
  11. Why I switched from Netlify back to GitHub Pages
  12. Why Have a Data Science Portfolio and What It Shows
  13. How to Install Google Scalable Nearest Neighbors (ScaNN) on Mac
  14. How Prototyping Can Help You to Get Buy-In
  15. Is Writing as Important as Coding?
  16. RecSys 2020: Takeaways and Notable Papers
  17. Appreciating the Present
  18. CareerFair - Day-to-day as an Applied Scientist at Amazon
  19. Routines and Tools to Optimize My Day (Guest Post by Susan Shu)
  20. How to Accomplish More with Less - Useful Tools & Routines
  21. Migrating Site Comments to Utterances
  22. How to Test Machine Learning Code and Systems
  23. Mailbag: Parsing Fields from PDFs—When to Use Machine Learning?
  24. Datacast Podcast - Effective Data Science with Eugene Yan
  25. How Reading Papers Helps You Be a More Effective Data Scientist
  26. Mailbag: I'm Now a Senior DS—How should I Approach this?
  27. Embrace Beginner's Mind; Avoid The Wrong Way To Be An Expert
  28. NLP for Supervised Learning - A Brief Survey
  29. Unpopular Opinion: Data Scientists Should be More End-to-End
  30. Adding a Checkbox & Download Button to a FastAPI-HTML app
  31. What I Did Not Learn About Writing In School
  32. Georgia Tech's OMSCS FAQ (based on my experience)
  33. How to Set Up a HTML App with FastAPI, Jinja, Forms & Templates
  34. Why You Need to Follow Up After Your Data Science Project
  35. What I Do During A Data Science Project To Deliver Success
  36. How to Update a GitHub Profile README Automatically
  37. The 85% Rule: When Giving It Your 100% Gets You Less than 85%
  38. My Notes From Spark+AI Summit 2020 (Application-Specific Talks)
  39. My Notes From Spark+AI Summit 2020 (Application-Agnostic Talks)
  40. How to Set Up a Python Project For Automation and Collaboration
  41. Mailbag: Qns on the Intersection of Data Science and Business
  42. Why Are My Airflow Jobs Running “One Day Late”?
  43. What I Do Before a Data Science Project to Ensure Success
  44. What I Love about Scrum for Data Science
  45. How to Apply Crocker's Law for Feedback and Growth
  46. A Practical Guide to Maintaining Machine Learning in Production
  47. 6 Little-Known Challenges After Deploying Machine Learning
  48. How to Write: Advice from David Perell and Sahil Lavingia
  49. A Hackathon Where the Dinkiest Idea Won. Why?
  50. Serendipity: Accuracy’s Unpopular Best Friend in Recommenders
  51. How to Give a Kick-Ass Data Science Talk
  52. Commando, Soldier, Police and Your Career Choices
  53. Stop Taking Regular Notes; Use a Zettelkasten Instead
  54. Writing is Learning: How I Learned an Easier Way to Write
  55. Simpler Experimentation with Jupyter, Papermill, and MLflow
  56. My Journey from Psych Grad to Leading Data Science at Lazada
  57. DataScience SG Meetup - RecSys, Beyond the Baseline
  58. Beating the Baseline Recommender with Graph & NLP in Pytorch
  59. Building a Strong Baseline Recommender in PyTorch, on a Laptop

2019 12

  1. OMSCS CS6200 (Introduction to OS) Review and Tips
  2. DataScience SG x ODSC Meetup - Applying ML to Healthcare
  3. OLX Prod Tech 2019 Keynote - Asia's Tech Giants & SuperApps
  4. OMSCS CS6750 (Human Computer Interaction) Review and Tips
  5. Goodbye Wordpress, Hello Jekyll!
  6. OMSCS CS6440 (Intro to Health Informatics) Review and Tips
  7. OMSCS CS7646 (Machine Learning for Trading) Review and Tips
  8. What does a Data Scientist really do?
  9. DATAx - A Production ML system for SEA's Biggest Hospital Group
  10. Data Science and Agile (Frameworks for Effectiveness)
  11. Data Science and Agile (What Works, and What Doesn't)
  12. DataScience SG Meetup - Panel On the Different Roles in Data

2018 7

  1. OMSCS CS6601 (Artificial Intelligence) Review and Tips
  2. GovTech Conference - Data Science and Agile—Can or Not?
  3. OMSCS CS6460 (Education Technology) Review and Tips
  4. OMSCS CS7642 (Reinforcement Learning) Review and Tips
  5. Big Data & Analytics Summit - Data Science Challenges @ Lazada
  6. Building a Strong Data Science Team Culture
  7. INSEAD Lunchtime Talks - How Lazada uses Data

2017 11

  1. OMSCS CS7641 (Machine Learning) Review and Tips
  2. My first 100 days as Data Science Lead
  3. SMU - What is Data Analytics and How do I get into it?
  4. OMSCS CS6300 (Software Development Process) Review and Tips
  5. Tech in Asia - My Journey in Data Science and Advice for others
  6. SMU Masters in IT - How to get started in Data Science
  7. How to get started in Data Science
  8. OMSCS CS6476 (Computer Vision) Review and Tips
  9. One way to help a data science team innovate successfully
  10. Product Categorization API Part 3: Creating an API
  11. Image search is now live!

2016 8

  1. Product Classification API Part 2: Data Preparation
  2. Strata x Hadoop 2016 - How Lazada Ranks Products
  3. Image classification API is now live!
  4. I'm going back to school
  5. SortMySkills is now live!
  6. Product Classification API Part 1: Data Acquisition
  7. Thoughts on Functional Programming in Scala Course (Coursera)
  8. First post!

2015 2

  1. DataKind Singapore’s Latest Project Accelerator
  2. DataScience SG Meetup - How we got top 3% in Kaggle