AI Engineer

What you will do:

• Build GenAI solutions for insurance. Design and ship production-grade LLM and generative AI features that solve real underwriting, claims and policy-servicing problems.
• Create agentic workflows. Develop AI agents with tool calling, orchestration and multi-step reasoning that can run reliably inside business processes.
• Automate document work. Build capabilities for document classification, data extraction and summarisation.
• Choose the right model. Assess various models from Azure AI, define routing strategies that balance quality, latency, reliability and cost.
• Measure quality. Set up evaluation suites, structured outputs and guardrails, and run automated regression tests so quality stays visible as the product changes.
• Tune and operate. Optimise for latency, token usage and scale; monitor production systems and lead root-cause analysis when quality or performance slips.
• Integrate and collaborate. Connect AI services to backend APIs, databases and enterprise workflows alongside Core Engineering, Product and Solutions teams.
• Lead the team. Mentor AI engineers, shape engineering standards, and keep evaluating new models and frameworks for fit.

What you will bring:

• Python and applied AI: strong hands-on delivery of AI/ML applications.
• GenAI foundations: LLMs, agents and function calling.
• Quality engineering: prompt design, structured outputs, guardrails, evaluation and AI observability.
• Azure AI stack: Azure AI, Microsoft Foundry and Azure OpenAI.
• Agent frameworks: Microsoft Agent Framework, LangGraph, Semantic Kernel or similar.
• Foundation models: working experience with OpenAI, Anthropic Claude or comparable providers.
• Backend skills: REST APIs, asynchronous processing, PostgreSQL (vector search is a plus).
• Delivery tooling: Git, Docker, CI/CD with Azure DevOps or GitHub Actions, and AI-assisted development tools such as Claude Code and GitHub Copilot.

Qualification:

• 6–10 years in AI engineering, ML engineering, applied AI, or software engineering with substantial GenAI/LLM work.
• Proven production delivery: you have taken AI solutions from experiment and evaluation through deployment and monitoring, beyond prototypes.
• Engineering depth: solid grounding in system design, scalability and maintainability, with sharp analytical problem-solving.
• Nice to have: enterprise workflow experience and insurance domain knowledge.