Gen AI Engineer

Remote

AI Agent Development and Orchestration

We are looking for an AI engineer to build and deploy AI agents that use enterprise data, call tools and coordinate multi-step business workflows. The role covers agent implementation, orchestration, integration, evaluation and production support.

Must have skills

- Strong Python development and API engineering, using FastAPI or a comparable framework, with testing and maintainable production code.
- Hands-on development of LLM-based agents that use tool or function calling, structured outputs, context and conversation state.
- Agent orchestration using LangGraph, LangChain, Microsoft Agent Framework, CrewAI or an equivalent framework. Candidates should demonstrate depth in at least one.
- Experience coordinating agents and workflows through routing, state management, retries, error handling and human approval steps.
- Retrieval-Augmented Generation (RAG), embeddings and vector search, plus integration with enterprise APIs, databases and documents.
- Evaluation,



tracing and guardrails for agent quality and safety; secure handling of data, credentials and tool permissions.

Key responsibilities

- Translate business processes into agent designs with transparent responsibilities, tools, success criteria and escalation paths.
- Build and orchestrate agents that retrieve information, execute approved actions and hand work between agents or people.
- Integrate LLMs and enterprise systems; deploy services using containers and CI/CD on the required cloud platform.
- Measure task success, accuracy, latency and cost; improve prompts, retrieval, routing and failure recovery using evaluation results.

Preferred experience

Azure OpenAI or other managed LLM services; Model Context Protocol (MCP); multi-agent systems; asynchronous processing; knowledge graphs; experience deploying and supporting AI applications at scale.

📌 Generative AI Engineer (India)
🏢 iShare
📍 India