Skip to content

Forem

Marcus Chen

Senior ML Engineer based in Austin. I write about ML evaluation, fine-tuning, and why your evals are probably lying to you. The model is the easy part.

Joined on Apr 3, 2026

May 26

Prefix caching in vLLM under multi-tenant agent traffic

#llm #mlops #infrastructure #pytorch

4 min read

May 25

We Audited Our Agent Tool-Call Traces. Half Our Eval Data Was Garbage.

#mlops #llm #machinelearning #infrastructure

4 min read

May 22

Why Your LLM Eval Harness Is Lying to You (And How to Fix It)

#mlops #llm #machinelearning #devops

4 min read

May 21

Measuring AI Gateway Failover: 30 Days of Production Data

#mlops #llm #infrastructure #devops

3 min read

Apr 7

What Gemma 4's multi-token prediction head actually means for your eval pipeline

#ai #programming #webdev #future

5 min read

Apr 3

Mastering Local AI Agents for Everyday Programming in 2026

#ai #programming #productivity

2 min read

loading...