I build production ML systems that work.
AI Engineer focused on RAG pipelines, LLM monitoring, and MLOps infrastructure. I ship systems that run reliably at scale.
What I Do
What I Build
Production ML systems — RAG pipelines, LLM applications, monitoring infrastructure, and the MLOps tooling that keeps them healthy. I focus on systems that serve real users, not just notebooks that impress in demos.
How I Work
Systems thinking first. I start with constraints, design for observability, and build incrementally. Every system I ship includes evaluation metrics, monitoring, and a path to iterate. No black boxes.
What I Care About
Reliability over novelty. I'd rather ship a well-monitored baseline than a fragile state-of-the-art system. The goal is production impact, not paper citations.
Featured Projects
RAG Pipeline for Enterprise Search
End-to-end retrieval-augmented generation system serving 10K+ daily queries with sub-second latency.
LLM Observability Platform
Monitoring and tracing infrastructure for LLM applications — catch regressions before users report them.
MLOps Platform for Model Deployment
Internal platform for deploying, versioning, and monitoring ML models — from training to production in hours, not weeks.
Interested in working together?
Currently exploring new opportunities in AI infrastructure and MLOps.
Get in Touch