Principal Engineer · AWS Community Builder

Vijay Kodam

I build and scale Kubernetes platforms and production AI systems on AWS.

Kubernetes · AWS · Agentic AI · Helsinki, Finland

Vijay Kodam

vijay@helsinki:~$ _

##Recent posts

all posts →
Catch silent model downgrades in Claude Code AI Lab Ornith 35B writes its own training scaffold: I put the self-improving coding model to the test on a Mac Mini M4 Pro AI Lab Monitoring Claude Code with Apple Containers Instead of Docker Co-authored LLM Inference Internals: KV Cache, Flash Attention, and Optimizing for Apple Silicon Co-authored I Ran an 80B Coding Model Locally with Claude Code. It Took 1 Hour Instead of 9 Minutes. Here's What Was Wrong. Co-authored