Eugene Yan
Evaluating Long-Context Question & Answer Systems
AI Engineer 2025 - Improving RecSys & Search with LLM techniques
Exceptional Leadership: Some Qualities, Behaviors, and Styles
Building News Agents for Daily News Recaps with MCP, Q, and tmux
An LLM-as-Judge Won't Save The Product—Fixing Your Process Will
Frequently Asked Questions about My Writing Process
NVIDIA GTC 2025 - Building LLM-Powered Applications
Improving Recommendation Systems & Search in the Age of LLMs
Building AI Reading Club: Features & Behind the Scenes
2024 Year in Review
A Spark of the Anti-AI Butlerian Jihad (on Bluesky)
Seemingly Paradoxical Rules of Writing
How to Run a Weekly Paper Club (and Build a Learning Community)
My Minimal MacBook Pro Setup Guide
39 Lessons on Building ML Systems, Scaling, Execution, and More
AlignEval: Building an App to Make Evals Easy, Fun, and Automated
Weights & Biases LLM-Evaluator Hackathon - Hackathon Judge
Building the Same App Using Various Web Frameworks
Evaluating the Effectiveness of LLM-Evaluators (aka LLM-as-Judge)
How to Interview and Hire ML/AI Engineers
AI Engineer 2024 Keynote - What We Learned from a Year of LLMs
Netflix PRS 2024 - Applying LLMs to Recommendation Experiences
Prompting Fundamentals and How to Apply them Effectively
What We've Learned From A Year of Building with LLMs
Building an AI Coach to Help Tame My Monkey Mind
Task-Specific LLM Evals that Do & Don't Work
Don't Mock Machine Learning Models In Unit Tests
How to Generate and Use Synthetic Data for Finetuning
Language Modeling Reading List (to Start Your Paper Club)
2023 Year in Review
Push Notifications: What to Push, What Not to Push, and How Often
Out-of-Domain Finetuning to Bootstrap Hallucination Detection
Reflections on AI Engineer Summit 2023
AI Engineer 2023 Keynote - Building Blocks for LLM Systems
Evaluation & Hallucination Detection for Abstractive Summaries
How to Match LLM Patterns to Problems
Patterns for Building LLM-based Systems & Products
Obsidian-Copilot: An Assistant for Writing & Reflecting
Some Intuition on Attention and the Transformer
Open-LLMs - A list of LLMs for Commercial Use
Interacting with LLMs with Minimal Chat
More Design Patterns For Machine Learning Systems
Raspberry-LLM - Making My Raspberry Pico a Little Smarter
Experimenting with LLMs to Research, Reflect, and Plan
LLM-powered Biographies
How to Write Data Labeling/Annotation Guidelines
Content Moderation & Fraud Detection - Patterns in Industry
Mechanisms for Effective Technical Teams
Mechanisms for Effective Machine Learning Projects
Goodbye Roam Research, Hello Obsidian
What To Do If Dependency Teams Can’t Help
2022 in Review & 2023 Goals
Autoencoders and Diffusers: A Brief Comparison
Text-to-Image: Diffusion, Text Conditioning, Guidance, Latent Space
RecSys 2022: Recap, Favorite Papers, and Lessons
RecSys 2022 Keynote - Is the Juice Worth the Squeeze?
Writing Robust Tests for Data & Machine Learning Pipelines
Simplicity is An Advantage but Sadly Complexity Sells Better
Uncommon Uses of Python in Commonly Used Libraries
Why You Should Write Weekly 15-5s
Design Patterns in Machine Learning Code and Systems
What I Wish I Knew About Onboarding Effectively
Bandits for Recommender Systems
How to Measure and Mitigate Position Bias
Counterfactual Evaluation for Recommendation Systems
Traversing High-Level Intent and Low-Level Requirements
Data Science Project Quick-Start
Mailbag: How to Define a Data Team's Vision and Roadmap
Red Flags to Look Out for When Joining a Data Team
How to Keep Learning about Machine Learning
The Data Scientist Show - Building end-to-end ML systems
2021 Year in Review
Informal Mentors Grew into ApplyingML.com!
5 Lessons I Learned from Writing Online (Guest post by Susan Shu)
What I Learned from Writing Online - For Fellow Non-Writers
RecSys 2021 - Papers and Talks to Chew on
The First Rule of Machine Learning: Start without Machine Learning
MLOps Community - System Design for RecSys & Search
Reinforcement Learning for Recommendations and Search
Amazon Science - Eugene Yan and the Art of Writing about Science
Bootstrapping Labels via ___ Supervision & Human-In-The-Loop
Mailbag: How to Bootstrap Labels for Relevant Docs in Search
SF Big Analytics - System Design for RecSys & Search
Influencing without Authority for Data Scientists
System Design for Recommendations and Search
Patterns for Personalization in Recommendations and Search
Towards Data Science - Author Spotlight with Eugene Yan
The Metagame of Applying Machine Learning
Search: Query Matching via Lexical, Graph, and Embedding Methods
My Impostor Syndrome Stories (Guest Post by Susan Shu)
How to Live with Chronic Imposter Syndrome
Planning Your Career: Values and Superpowers
Bukalapak - Fireside Chat with the Data Science team
TalkPython - What ML can Teach Us About Life
Choosing Problems in Data Science and Machine Learning
Seven Habits that Shaped My Last Decade
How to Write Design Docs for Machine Learning Systems
How to Write Better with The Why, What, How Framework
Feature Stores: A Hierarchy of Needs
How to Win a Data Hackathon (Hacklytics 2021)
DataTalksClub - Building an ML System; Behind the Scenes
Growing and Running Your Data Science Team
You Don't Really Need Another MOOC
DataTalksClub - The Importance Of Writing In A Tech Career
Mailbag: How to Get Experienced DS Resume Noticed by Recruiters?
Real-time Machine Learning For Recommendations
2021 Roadmap: Sharing, Helping, and Living More
2020 Retrospective: New Country, New Role, New Habit
Catch the Flying Daggers
How I’m Reflecting on 2020 and Planning for 2021
Alexey Grigorev on His Career, Data Science, and Writing
Mailbag: What's the Architecture for your Blog?
What Machine Learning Can Teach Us About Life - 7 Lessons
How to Prevent or Deal with a Data Science Role or Title Mismatch
Applied / Research Scientist, ML Engineer: What’s the Difference?
Chip Huyen on Her Career, Writing, and Machine Learning
Data Discovery Platforms and Their Open Source Solutions
Why I switched from Netlify back to GitHub Pages
Why Have a Data Science Portfolio and What It Shows
How to Install Google Scalable Nearest Neighbors (ScaNN) on Mac
How Prototyping Can Help You to Get Buy-In
Is Writing as Important as Coding?
RecSys 2020: Takeaways and Notable Papers
Appreciating the Present
CareerFair - Day-to-day as an Applied Scientist at Amazon
Routines and Tools to Optimize My Day (Guest Post by Susan Shu)
How to Accomplish More with Less - Useful Tools & Routines
Migrating Site Comments to Utterances
How to Test Machine Learning Code and Systems
Mailbag: Parsing Fields from PDFs—When to Use Machine Learning?
Datacast Podcast - Effective Data Science with Eugene Yan
How Reading Papers Helps You Be a More Effective Data Scientist
Mailbag: I'm Now a Senior DS—How should I Approach this?
Embrace Beginner's Mind; Avoid The Wrong Way To Be An Expert
NLP for Supervised Learning - A Brief Survey
Unpopular Opinion: Data Scientists Should be More End-to-End
Adding a Checkbox & Download Button to a FastAPI-HTML app
What I Did Not Learn About Writing In School
Georgia Tech's OMSCS FAQ (based on my experience)
How to Set Up a HTML App with FastAPI, Jinja, Forms & Templates
Why You Need to Follow Up After Your Data Science Project
What I Do During A Data Science Project To Deliver Success
How to Update a GitHub Profile README Automatically
The 85% Rule: When Giving It Your 100% Gets You Less than 85%
My Notes From Spark+AI Summit 2020 (Application-Specific Talks)
My Notes From Spark+AI Summit 2020 (Application-Agnostic Talks)
How to Set Up a Python Project For Automation and Collaboration
Mailbag: Qns on the Intersection of Data Science and Business
Why Are My Airflow Jobs Running “One Day Late”?
What I Do Before a Data Science Project to Ensure Success
What I Love about Scrum for Data Science
How to Apply Crocker's Law for Feedback and Growth
A Practical Guide to Maintaining Machine Learning in Production
6 Little-Known Challenges After Deploying Machine Learning
How to Write: Advice from David Perell and Sahil Lavingia
A Hackathon Where the Dinkiest Idea Won. Why?
Serendipity: Accuracy’s Unpopular Best Friend in Recommenders
How to Give a Kick-Ass Data Science Talk
Commando, Soldier, Police and Your Career Choices
Stop Taking Regular Notes; Use a Zettelkasten Instead
Writing is Learning: How I Learned an Easier Way to Write
Simpler Experimentation with Jupyter, Papermill, and MLflow
My Journey from Psych Grad to Leading Data Science at Lazada
DataScience SG Meetup - RecSys, Beyond the Baseline
Beating the Baseline Recommender with Graph & NLP in Pytorch
Building a Strong Baseline Recommender in PyTorch, on a Laptop
OMSCS CS6200 (Introduction to OS) Review and Tips
DataScience SG x ODSC Meetup - Applying ML to Healthcare
OLX Prod Tech 2019 Keynote - Asia's Tech Giants & SuperApps
OMSCS CS6750 (Human Computer Interaction) Review and Tips
Goodbye Wordpress, Hello Jekyll!
OMSCS CS6440 (Intro to Health Informatics) Review and Tips
OMSCS CS7646 (Machine Learning for Trading) Review and Tips
What does a Data Scientist really do?
DATAx - A Production ML system for SEA's Biggest Hospital Group
Data Science and Agile (Frameworks for Effectiveness)
Data Science and Agile (What Works, and What Doesn't)
DataScience SG Meetup - Panel On the Different Roles in Data
OMSCS CS6601 (Artificial Intelligence) Review and Tips
GovTech Conference - Data Science and Agile—Can or Not?
OMSCS CS6460 (Education Technology) Review and Tips
OMSCS CS7642 (Reinforcement Learning) Review and Tips
Big Data & Analytics Summit - Data Science Challenges @ Lazada
Building a Strong Data Science Team Culture
INSEAD Lunchtime Talks - How Lazada uses Data
OMSCS CS7641 (Machine Learning) Review and Tips
My first 100 days as Data Science Lead
SMU - What is Data Analytics and How do I get into it?
OMSCS CS6300 (Software Development Process) Review and Tips
Tech in Asia - My Journey in Data Science and Advice for others
SMU Masters in IT - How to get started in Data Science
How to get started in Data Science
OMSCS CS6476 (Computer Vision) Review and Tips
One way to help a data science team innovate successfully
Product Categorization API Part 3: Creating an API
Image search is now live!
Product Classification API Part 2: Data Preparation
Strata x Hadoop 2016 - How Lazada Ranks Products
Image classification API is now live!
I'm going back to school
SortMySkills is now live!
Product Classification API Part 1: Data Acquisition
Thoughts on Functional Programming in Scala Course (Coursera)
First post!
DataKind Singapore’s Latest Project Accelerator
DataScience SG Meetup - How we got top 3% in Kaggle