Machine Learning Engineer with 4 years of experience building LLM and retrieval systems that run in production. I specialize in retrieval-augmented generation, inference optimization, and the MLOps infrastructure that keeps ML systems reliable at scale, including drift detection, model registries, and automated retraining. My work spans the full lifecycle: training models on millions of users, deploying quantized models, and building streaming pipelines that catch model decay before it reaches users.
- LinkedIn: [https://www.linkedin.com/in/jay0101work/]