Key responsibilities 1. Build and ship.

Implement

GenAI features end to end on Azure - RAG pipelines, agents, APIs, and UI integrations - against enterprise systems and data.

- Embed and enable.

Work inside the delivery pods: pair with their engineers, remove blockers, and transfer GenAI skills so adoption sticks after you move on.
- Productionize. Add evaluation, observability, guardrails, caching, and CI/CD so prototypes become reliable, cost-productive services.
- Integrate securely. Connect to enterprise data with correct access control, secrets management, and compliance with enterprise security standards and handling of sensitive data.
- Iterate on quality. Use evaluation results and user feedback to improve grounding, accuracy, latency, and cost.
- Measure. Track delivery and quality metrics that roll up to the program's targets. Must-have qualifications • • • • 6+ years in software engineering, with 2+ years building GenAI/LLM applications in production.

Strong

Python (incl. async)



and Java (the primary enterprise application stack; Spring a plus); solid API and systems design.

Azure

GenAI hands-on: Azure OpenAI, Azure AI Foundry, Azure AI Search for RAG, Azure AI Document Intelligence (IDP), and Prompt Flow.

Agent frameworks: Microsoft Agent Framework / Semantic Kernel / AutoGen (or LangChain / LangGraph) and tool / function calling. Preferred • • • • RAG fundamentals: embeddings, chunking, vector search, reranking, and grounding.

Data platforms: Snowflake including Cortex AI (Cortex Search, LLM functions) and SQL, for accessing and grounding on enterprise data. Prompt engineering as versioned code; building and running evaluations.

DevOps: Azure DevOps / GitHub Actions, Docker, AKS / Azure Functions, and observability. • • Financial services or other regulated environments. Front-end (React) for AI-assisted UX; streaming and token level operations

📌 Senior AI Implementation (Mumbai)
🏢 wissen technology
📍 Mumbai