Key Responsibilities
- Design and implement agentic AI systems using frameworks like LangGraph or Semantic Kernel for clinical workflow automation
- Develop Retrieval-Augmented Generation (RAG) pipelines grounded in clinical guidelines and real-time patient data
- Architect scalable inference services with low-latency performance for clinical environments
- Build vector search infrastructure using Pinecone or Milvus to process fragmented clinical data
- Ensure AI systems comply with HIPAA and data privacy requirements
- Mentor engineers in AI-LLM/ML best practices and participate in code reviews
Requirements
- 5+ years of ML/LLM engineering experience with production-grade systems
- Deep expertise in LLM orchestration, tool-calling, and long-context document handling
- Proficiency with vector databases (Pinecone, Milvus) and MLOps tools (Docker, Kubernetes)
- Strong C#/.NET backend development skills for clinical platform integration
- Experience with automated testing, evaluation frameworks, and version control (Git)