GenAI / Agentic AI Engineer (LLM, LangGraph, RAG)

Job description

**Key Responsibilities** - Design, develop, and deploy AI-powered applications using LLMs, Agentic AI frameworks, and modern AI architectures. - Build and orchestrate multi-agent systems using LangGraph, A2A, MCP, and related frameworks. - Design and implement scalable RAG pipelines using vector databases, embeddings, and semantic search. - Develop REST APIs and AI services using Python, FastAPI, and Pydantic. - Integrate AI solutions with AWS, Azure, or GCP cloud services. - Build and optimize prompt engineering, tool-calling, and agent workflows. - Develop LLM evaluation, monitoring, and optimization frameworks. - Create AI-driven user experiences and business workflows powered by intelligent agents. - Collaborate with business, compliance, IT, and data teams to deliver enterprise AI solutions. - Leverage AI-assisted development practices for code generation, testing, documentation, and refactoring. - Implement cloud-native deployment strategies using Docker, CI/CD, and modern DevOps practices. - Stay updated on emerging GenAI, Agentic AI, and LLM technologies. **Required Skills** - 8+ years of Software Engineering or Data Science experience. - Minimum 2+ years of hands-on experience in Generative AI, LLMs, or Agentic AI solutions. - Strong expertise in Python development. - Experience building AI Agents using LangGraph and related agent frameworks. - Strong knowledge of LLMs, embeddings, prompt engineering, and tool integrations. - Hands-on experience with Retrieval-Augmented Generation (RAG) architectures. - Experience developing APIs using FastAPI and Pydantic. - Experience with MCP (Model Context Protocol) and A2A integrations. - Knowledge of cloud platforms such as AWS, Azure, or GCP. - Experience with Docker, CI/CD pipelines, and cloud-native architectures. **Preferred Skills** - Insurance or Annuities domain experience. - Experience with Azure OpenAI, AWS Bedrock, Vertex AI, or similar AI services. - Vector databases such as Pinecone, Weaviate, Chroma, or OpenSearch. - AI observability, evaluation, and governance frameworks. - Knowledge of MLOps and AI platform engineering. - Experience building production-grade AI applications.