Gen Ai Engineer

Job highlights

• Expertise in Azure OpenAI, RAG, vector search, Databricks or Microsoft Fabric, strong Python and SQL skills, experience with LLM evaluation and monitoring
• Build and deploy GenAI and agent-based AI solutions, deliver analytics use cases, ensure HIPAA compliance, mentor engineers, and establish team standards

To build AI solutions on our Databricks and Fabric platforms for US healthcare operations such as claims, payment integrity, care management and contact centre, and help our BI and ETL engineers grow into AI work. This is a hands-on role.

What you'll do

• Build and run GenAI and agent-based solutions end to end, from design through deployment and monitoring, using Azure OpenAI, AI Foundry and Databricks Mosaic AI.
• Deliver analytics use cases such as conversational analytics and text-to-SQL, document intelligence, automated insights and data-quality checks.
• Build RAG pipelines and vector search over Databricks, SharePoint and enterprise APIs.
• Set up evaluation (groundedness, hallucination, retrieval quality, regression) and monitoring (latency, tokens, cost, errors) for everything you ship.
• Keep solutions compliant with HIPAA and PHI requirements, including masking, access-controlled retrieval and prompt-injection protection.
• Work with operations leaders to find use cases worth building and prove their value.
• Mentor BI and ETL engineers and set up reusable standards for the team.

Must have

• Strong Python and SQL
• Azure OpenAI / AI Foundry, RAG, vector search, agents and tool calling
• Hands-on Databricks and/or Microsoft Fabric
• Experience evaluating and monitoring LLM solutions in production
• CI/CD and deployment on Azure

Good to have

• Understanding of Healthcare payer or provider data
• Semantic Kernel, LangGraph or AutoGen; MCP
• Copilot Studio / Microsoft Graph
• Classical ML and MLflow
• AI-102 or Databricks GenAI certification

In your first 12 months

• 2 - 3 AI use cases in production with measurable impact
• An evaluation and monitoring standard adopted by the team
• 3 - 5 internal engineers contributing to AI delivery

Work Mode: Hybrid (2 Days Work From Office in a week)
Shift Timing: 2 PM to 11 PM
Interview Process: 3 Technical Rounds(Final Round is F2F)

Regards,

[email protected]