AI Engineer

Job Title: AI Engineer About the Role We are looking for an experienced AI Engineer with deep expertise in Retrieval-Augmented Generation (RAG), AWS Bedrock, and agentic AI architectures. The ideal candidate will have strong backend development skills and hands-on experience with LangChain, Agent-to-Agent protocols, MCP, and advanced AI/ML techniques. This role involves designing, developing, and deploying intelligent, scalable AI solutions that leverage cutting-edge frameworks, vector databases, and embedding models.Key ResponsibilitiesDesign and implement AI-powered applications using RAG techniques and vector databases.Build and maintain scalable backend services with Java, Python, and Node.js.Develop and deploy autonomous agents using frameworks like LangChain or similar agentic frameworks.Integrate AI solutions with AWS Bedrock and related AWS services (S3, Lambda, SageMaker, etc.).Work with embedding models and vector DBs such as Pinecone, Weaviate, or FAISS.Implement agent-to-agent communication protocols and multi-agent task orchestration.Leverage MCP (Model Context Protocol) for structured LLM interactions.Collaborate with cross-functional teams to transition AI research into production-grade systems.Required Skills & Experience5+ years of backend development experience (Java, Python, Node.js).Proven expertise with AWS Cloud, specifically AWS Bedrock.Hands-on experience with LangChain and other agentic AI frameworks.Strong understanding of RAG architectures, vector DBs, and embeddings (OpenAI, Cohere, etc.).Experience with agent-to-agent protocols, LLM orchestration, and MCP.Knowledge of Microservices architecture using Python or Java.Familiarity with AI/ML fundamentals including embeddings, RAG, and prompt chaining.Nice to HaveExperience with other LLM providers (Anthropic, Mistral, Cohere, etc.).Exposure to prompt engineering and advanced chaining logic.DevOps/MLOps experience on AWS.