Description

Key Skills: Gen AI, LLM, v Lang chain, Retrieval-Augmented Generation (RAG)

Roles and Responsibilities:

• Architect and deliver GenAI solutions for document interpretation, automated decision workflows, feedback generation, dashboarding, data reconciliation, and approval management.
• Design agent-based workflows using LLMs, retrieval pipelines, and multi-agent orchestration frameworks (including LangChain/LangGraph and Azure AI Agents).
• Build composite AI architectures combining LLMs, search, business rules, embeddings, and analytics; implement robust context pipelines (chunking, prompting, memory, vector retrieval).
• Develop backend components and API integrations for AI agents using Python, Azure AI services, Azure Functions, and APIM; support MCP-based tool integrations.
• Own production readiness: CI/CD, automated testing, monitoring, performance optimization, and adherence to responsible AI standards and enterprise governance.

Skills Required:

• 4 - 6 years of AI engineering experience, including leading GenAI initiatives from concept to deployment in enterprise environments.
• Gen AI and LLM development for enterprise use cases.
• Python-based backend engineering with scalable APIs and microservices.
• Azure AI / Azure OpenAI, Azure Functions, and APIM experience for deploying AI capabilities.
• RAG-style retrieval fundamentals including embeddings, vector search, and context assembly (chunking, prompting, vector retrieval).

Good to Have:

• LangChain/LangGraph and Azure AI Agents for agentic workflows; experience with LlamaIndex and Hugging Face Transformers.
• Vector database experience (Azure AI Search, Pinecone, FAISS) and MCP-based enterprise tool chains.
• Experience with multi-agent orchestration patterns (tool-calling, DAG orchestration) and evaluation of new GenAI use cases.

Education: Bachelor's or Master's degree in Computer Science, Engineering, or related technical discipline

Key Skills

Education

Any Graduate