Senior AI Engineer GenAI / Agentic AI / AWS Bedrock

Job Title: Senior AI Engineer – GenAI / Agentic AI / AWS Bedrock Experience: 6+ Years Location: Hyderabad | Gurugram | Pune | Bengaluru | Mohali | Panchkula Fulltime Shift: Late Noon Shift (4:00 PM IST onwards) Job Summary We are looking for an experienced Senior AI Engineer to design, build, and deploy enterprise-grade Generative AI applications. The ideal candidate will have strong expertise in Python, AWS, Amazon Bedrock, Retrieval-Augmented Generation (RAG), Agentic AI, and Model Context Protocol (MCP) , with hands-on experience building production-ready AI solutions. This role requires someone who can architect scalable AI systems, develop intelligent AI agents, optimize retrieval pipelines, and integrate Large Language Models into enterprise applications while ensuring performance, security, and reliability. Key Responsibilities Design, develop, and deploy enterprise-grade AI and LLM-powered applications. Build and maintain Retrieval-Augmented Generation (RAG) pipelines using vector databases and document retrieval systems. Develop AI agents and multi-agent workflows using modern agent orchestration frameworks. Design backend services and REST APIs using Python and FastAPI. Implement semantic search, hybrid search, embeddings, reranking, and retrieval optimization techniques. Integrate foundation models including OpenAI GPT, Anthropic Claude, Meta Llama, Google Gemini, and Amazon Nova through Amazon Bedrock. Build tool-calling architectures, structured output pipelines, and prompt engineering workflows. Develop and integrate MCP (Model Context Protocol) servers and MCP client implementations. Implement streaming AI responses using Server-Sent Events (SSE) or WebSockets. Optimize AI applications for scalability, latency, reliability, and cost efficiency. Implement observability, monitoring, evaluation, guardrails, and hallucination mitigation for production AI systems. Collaborate with engineering, DevOps, and cloud teams to deploy production-ready AI applications on AWS. Follow secure software development practices, including authentication, authorization, and cloud security. Required Skills 6+ years of software development experience with strong expertise in Python. Hands-on experience building production-grade Generative AI or LLM applications. Strong experience designing and implementing RAG-based applications. Experience building AI agents and agentic workflows. Hands-on experience with one or more frameworks: LangChain LangGraph CrewAI AutoGen Semantic Kernel Experience with MCP (Model Context Protocol) server development and client integrations. Strong knowledge of: Embeddings Vector databases Semantic search Hybrid search BM25 Reranking Retrieval optimization Experience with FastAPI and REST API development. Hands-on experience with vector databases such as Pinecone, Qdrant, ChromaDB, or Weaviate. Strong understanding of prompt engineering, structured outputs, tool calling, and AI orchestration. Experience with foundation models including GPT, Claude, Gemini, Llama, Amazon Nova, or similar. Strong AWS experience, specifically: Amazon Bedrock Amazon S3 OpenSearch AWS Lambda ECS/EKS Experience with SQL, Git, GitHub, and GitHub Actions. Understanding of authentication, authorization, and secure AI application development. Preferred Skills Docker and Kubernetes AI observability platforms such as Langfuse, Arize Phoenix, or Helicone LLM evaluation frameworks such as LangSmith, Ragas, or DeepEval Node.js or TypeScript Terraform or CloudFormation MLOps / LLMOps CI/CD pipeline implementation Experience deploying enterprise-scale AI solutions on AWS What We're Looking For The ideal candidate is passionate about building enterprise AI products and has hands-on experience delivering production-ready GenAI solutions. You should be comfortable working across the entire AI application lifecycle—from backend development and retrieval systems to agent orchestration and cloud deployment. If you have deep expertise in Python, AWS Bedrock, RAG, Agentic AI, MCP, and modern LLM frameworks , we'd love to hear from you.