Role Description

• Develop and deploy applications that use LLMs (e.g., chatbots, document analyzers, code generators).
• Fine-tune and evaluate LLMs using custom datasets.
• Implement RAG (retrieval-augmented generation), agents, or multi-step reasoning workflows.
• Integrate GenAI pipelines into production systems using ML Ops tools (e.g., ML flow, Azure ML, Databricks).
• Build and monitor inference APIs with performance and cost considerations.
• Apply prompt engineering, vector databases, and orchestration frameworks.
• Ensure responsible AI practices, including model explainability, bias mitigation, and security

Requirement

• Insurance experience in Corporate & Speciality space
• Experience in prompt engineering, Copilot Studio