Posted on: 16/11/2026
Senior AI Engineer – Agentic AI / MCP
Experience: 6–12+ years
Location: Bangalore
Role Overview
We are looking for a hands-on Senior AI Engineer with strong expertise in Agentic AI, AI agent development, LangGraph and MCP Server development. The candidate will design, build and deploy production-grade AI agents and intelligent workflows, integrating LLMs with enterprise systems, APIs and data sources.
Key Responsibilities
Design and develop autonomous AI agents and multi-agent workflows.
Build and deploy MCP servers to expose enterprise tools, APIs and data securely to AI agents.
Develop agentic workflows using LangGraph, LangChain and function/tool calling.
Build enterprise RAG solutions, including embeddings, vector databases, retrieval and context engineering.
Integrate LLMs with enterprise applications, databases and external services.
Implement prompt engineering, context management, memory and human-in-the-loop workflows.
Deploy, monitor and optimize production AI applications.
Implement security measures, including prompt-injection protection, PII handling, authentication and access controls.
Improve AI solution performance, scalability, reliability and cost efficiency.
Mandatory Skills
Strong hands-on experience in Python.
Practical experience in AI Agent Development and Agentic AI.
Hands-on experience with LangGraph.
Proven experience in MCP Server development (building servers, not just consuming MCP tools).
Experience developing LLM-powered applications and tool-calling workflows.
Strong understanding of RAG, LLM integration and production AI systems.
Good-to-Have Skills
Azure OpenAI, Azure AI Foundry, AWS Bedrock or other LLM platforms.
LangChain, vector databases and semantic search.
Multi-agent frameworks and advanced context engineering.
Docker, Kubernetes, CI/CD and cloud deployment.
LLM evaluation, observability, guardrails and AI security.
Ideal Candidate
A hands-on AI engineer who has independently built and deployed production-ready Agentic AI solutions, developed MCP servers, and implemented LangGraph-based workflows using Python.
Did you find something suspicious?