An AI engineer focused on production-grade retrieval, agentic LLM systems, and AI evaluation.
I build systems that move from research to dependable production, with a strong focus on evaluation, reliability, and human-centered AI products.
Current Focus
Current focus (2025)
- Building reliable retrieval pipelines for LLM applications, with strong evaluation loops.
- Exploring agentic workflows that are safe, inspectable, and useful in real products.
- Iterating on evaluation methods for quality, grounding, and robustness.
Selected Work
Project One (Placeholder)
A short description of the problem this project tackles.
Project Two (Placeholder)
One sentence on what you built or explored, and why it mattered.
Project Three (Placeholder)
A compact “what + approach” teaser.
How I Work
Start with metrics and failure modes before models.
Prefer simple baselines and tight evaluation loops.
Ship, observe, iterate.
Design for reliability, not just demos.