Lead AI Engineer
Regeneron
August 24, 2026
On-site
Tarrytown, NY
IT
Position Overview
- Architect and deliver enterprise-scale AI capabilities spanning intelligent agents, LLM-powered applications, and AI platform services.
- Lead a team of engineers, drive cross-functional collaboration, and communicate AI strategy to senior stakeholders.
Key Responsibilities
- Lead end-to-end design, development, and deployment of production-grade enterprise AI applications and LLM-powered systems (quality, security, scalability).
- Design and build AI Agents/autonomous systems using LangChain, LangGraph, Strands, CrewAI (ReAct, tool-use, planning, memory management).
- Develop and operate MCP (Model Context Protocol) servers for secure integration with enterprise data sources.
- Apply prompt engineering, fine-tuning, and RAG to build context-aware applications.
- Architect/manage vector databases (Milvus DB preferred) for semantic search and RAG pipelines.
- Architect RESTful APIs exposing AI capabilities to internal and business applications.
- Administer/evolve an enterprise LLM + AI Gateway (model routing, access controls, rate limiting, observability, multi-model orchestration).
- Evaluate and onboard new foundation models (OpenAI, Anthropic, AWS Bedrock, etc.) per security/compliance.
- Lead/mentor engineers, conduct code reviews, set technical standards, and troubleshoot complex issues.
- Partner with business, data science, and clinical research teams; serve as primary technical point of contact; engage external vendors/cloud providers.
Requirements & Qualifications
- Bachelor’s/Master’s/Ph.D. in Computer Science/Engineering/AI or related.
- 7–10 years software + AI engineering; 3+ years leading or senior IC.
- Expert Python (FastAPI for production REST APIs).
- Hands-on AI Agents, MCP servers, LLM applications (LangChain/LangGraph/Strands/CrewAI).
- Vector DB experience (Milvus preferred) for RAG/semantic search.
- LLM gateway administration (routing, observability, governance, orchestration).
- Foundation model experience (OpenAI, Anthropic, AWS Bedrock, etc.).
- AWS knowledge (SageMaker, Bedrock, EKS, Lambda, S3); Kubernetes/CI/CD a plus.
- Biotech/pharma/healthcare experience preferred.
- AWS Certified Machine Learning – Specialty.
Nice to Have
- AWS Certified Solutions Architect – Professional; CKA.
Soft Skills
- Strong communication with engineering and executives; proven team leadership; pragmatic problem-solving.
Application Instructions
- Apply now; contact recruiter for questions.
- Architect and deliver enterprise-scale AI capabilities spanning intelligent agents, LLM-powered applications, and AI platform services.
- Lead a team of engineers, drive cross-functional collaboration, and communicate AI strategy to senior stakeholders.
Key Responsibilities
- Lead end-to-end design, development, and deployment of production-grade enterprise AI applications and LLM-powered systems (quality, security, scalability).
- Design and build AI Agents/autonomous systems using LangChain, LangGraph, Strands, CrewAI (ReAct, tool-use, planning, memory management).
- Develop and operate MCP (Model Context Protocol) servers for secure integration with enterprise data sources.
- Apply prompt engineering, fine-tuning, and RAG to build context-aware applications.
- Architect/manage vector databases (Milvus DB preferred) for semantic search and RAG pipelines.
- Architect RESTful APIs exposing AI capabilities to internal and business applications.
- Administer/evolve an enterprise LLM + AI Gateway (model routing, access controls, rate limiting, observability, multi-model orchestration).
- Evaluate and onboard new foundation models (OpenAI, Anthropic, AWS Bedrock, etc.) per security/compliance.
- Lead/mentor engineers, conduct code reviews, set technical standards, and troubleshoot complex issues.
- Partner with business, data science, and clinical research teams; serve as primary technical point of contact; engage external vendors/cloud providers.
Requirements & Qualifications
- Bachelor’s/Master’s/Ph.D. in Computer Science/Engineering/AI or related.
- 7–10 years software + AI engineering; 3+ years leading or senior IC.
- Expert Python (FastAPI for production REST APIs).
- Hands-on AI Agents, MCP servers, LLM applications (LangChain/LangGraph/Strands/CrewAI).
- Vector DB experience (Milvus preferred) for RAG/semantic search.
- LLM gateway administration (routing, observability, governance, orchestration).
- Foundation model experience (OpenAI, Anthropic, AWS Bedrock, etc.).
- AWS knowledge (SageMaker, Bedrock, EKS, Lambda, S3); Kubernetes/CI/CD a plus.
- Biotech/pharma/healthcare experience preferred.
- AWS Certified Machine Learning – Specialty.
Nice to Have
- AWS Certified Solutions Architect – Professional; CKA.
Soft Skills
- Strong communication with engineering and executives; proven team leadership; pragmatic problem-solving.
Application Instructions
- Apply now; contact recruiter for questions.