Now

Work

Doozie Software Solutions

Working on LLM and full-stack problems. Most of my time goes into web applications, product features, and practical AI workflows.

Learning

Personal AI Lab

Building through a public 12-station LLM engineering lab: SFT, structured output, evals, vLLM serving, guardrails, RAG, and observability. The goal is to feed a stronger V2 of the AI Risk Evaluation Workbench.

Current build

SFT risk classifier

Starting with Station 01 and Station 02: prove the fine-tuning loop, build a small AI-risk dataset, validate it, then scale only after the loop works.

Personal

Quiet baseline

Calm music, reading habits, health, and how I try to think about attention and distraction in a noisy world.

See notes →

Writing

Build notes and essays

Writing here when something needs a longer explanation. Shorter notes may also go to Hashnode.

Public updates

Short notes on X

I use X for quick updates on AI tools, automation ideas, coding, and small lessons from building.