About the role
We are looking for a hands-on Agentic AI Engineer with strong experience in designing, developing, and deploying production-grade Generative AI and Agentic AI applications. The ideal candidate should have practical implementation experience building autonomous AI agents, multi-agent workflows, LLM-powered applications, and intelligent automation solutions.
The candidate must have strong Python programming skills, expertise in agent orchestration frameworks, LLM integration, RAG architecture, tool calling, and experience taking AI solutions from prototype to production.
Key ResponsibilitiesDesign, develop, and deploy production-grade Agentic AI applications and autonomous AI agents.
Build multi-agent systems using frameworks such as LangGraph, CrewAI, AutoGen, or equivalent.
Develop agent orchestration, planning, reasoning, memory management, and tool-calling capabilities.
Implement LLM-powered applications using OpenAI, Azure OpenAI, Anthropic Claude, AWS Bedrock, or Google Vertex AI.
Design and implement RAG pipelines using vector databases, embeddings, semantic search, and knowledge retrieval.
Develop MCP-based integrations to connect AI agents with external tools, APIs, databases, and enterprise systems.
Implement agent evaluation, observability, monitoring, guardrails, and error-handling mechanisms.
Optimize LLM performance, latency, token consumption, and response quality.
Build scalable backend services and APIs using Python and frameworks such as FastAPI.
3–8 years of overall software engineering / AI engineering experience.
Strong hands-on Python development experience.
Practical experience building Agentic AI applications, not just theoretical knowledge or POCs.
At least 1–2 production-grade GenAI / Agentic AI implementations.
Ability to independently design, develop, test, and deploy AI agents.
Strong understanding of LLM architecture, agent orchestration, RAG, and MCP.
Experience working on enterprise use cases with measurable business outcomes.