Senior AI Engineer with 4 years building production ML/AI systems for Fortune 500 pharmaceutical clients (J&J, Roche). Specialized in healthcare NLP, RAG architectures, and cost-optimized LLM deployments. Led AI development in lean teams (4-5 engineers), shipping 2 commercial AI products adopted by 7+ U.S. pharma companies. Successfully optimized AI systems to reduce LLM costs and latency by while maintaining baseline accuracy through hybrid architectures.
- Successfully delivered 2 end-to-end AI products currently used by multiple clients and their teams in the US.
- Integrated Generative AI solutions in medical products
- Designed and implemented scalable AI Solutions
- Focus: End-to-end RAG architecture designed for large-scale, multi-user concurrency. Demonstrates how to integrate a basic RAG approach with advanced deployment strategies (Kubernetes, CI/CD, etc.).
- Focus: Lightweight, local-first RAG agent for secure document QA — PDF ingestion, LangChain processing, Ollama LLM integration, Chroma vector store, and Docker/CI-friendly deployment for scalable multi-user workflows.
- Focus: Exploration of diverse RAG methodologies—semantic chunking, multi-query fusion, hybrid search, self-reflection, etc.
- Generative AI & LLMs: Production-grade LLM applications, Advanced RAG pipelines
- Deployment & Architecture: Containerization (Docker), Kubernetes (AWS EKS), CI/CD (GitHub Actions), End-to-End Integration
- Team Management: Experience overseeing small teams, mentoring junior members, and ensuring smooth project delivery.
- Client Engagement: Collaborated closely with clients to understand requirements and align technical solutions.
- Reasoning Models
- Model Distillation Techniques
- AI Agents
