Lead the architecture, design, and implementation of GenAI/Agentic AI based solutions into real-world enterprise-ready applications.
Collaborate with AI/ML teams to operationalize models using APIs, embeddings, vector databases, and prompt engineering techniques.
Own full-stack development and integration of GenAI features into web/mobile applications.
Establish best practices for scalable, secure, and maintainable AI-powered application development.
Optimize application performance, latency, and reliability of AI features in production.
Drive DevOps practices for continuous delivery and monitoring of AI-enabled services in production.
Mentor engineers and guide code reviews, architectural decisions, and DevOps practices.
Evaluate emerging GenAI tools and LLM frameworks and make build-vs-buy recommendations.
Oversee application-level development, testing, and deployment.
Lead technical delivery of AI-powered features for horizonal and vertical healthcare use cases while ensuring compliance with enterprise integration standards.
Requirements
10+ years of full-stack application engineering experience, with at least 2 years leading cross-functional teams.
Architect agentic AI systems using LangChain/LangGraph, CrewAI, and OpenAI Agentic SDK
Design RAG architectures with hybrid search, vector databases, and knowledge graphs
Optimize multi-agent workflows using reinforcement learning, dynamic orchestration, and memory management.
Deploy scalable AI solutions on AWS/GCP (SageMaker, Vertex AI, Bedrock API).
8+ years in AI/ML engineering with large-scale deployment expertise.
Proficient in prompt engineering (zero-shot, chain-of-thought) and LLM evaluation.
Strong background in insurance/financial domains (preferred)
Agile collaborator with GitHub/VS Code proficiency