Architecting LLM and agentic AI pipelines. Specializing in model fine-tuning, inference optimization, and Industrial Applications

I’m a Machine Learning Engineer with experience designing and deploying LLM-based agentic systems, retrieval-augmented generation (RAG) pipelines, and scalable AI workflows. At Aitomatic, I led development of domain-specific LLMs, optimized inference systems, and contributed to open-source initiatives like OpenSSA and SemiKong. At Harvard Medical School, I built clinical NLP tools that achieved real-world adoption at Massachusetts General Hospital, reducing annotation time by 90%. I specialize in LLM fine-tuning (LoRA and full-parameter), inference optimization, model context integration, and verticalized agentic architectures. I’m passionate about building production-grade AI that combines speed, trust, and domain-specific reasoning. In my next role, I’m excited to work on cutting-edge LLM systems, scalable agent pipelines, and AI infrastructure that drives real-world impact.