Overview
The AI Engineer will join a technology team focused on transforming underwriting, claims, and operational processes through innovative Generative AI solutions. This role involves designing and delivering enterprise-level AI applications, integrating AI into various systems, and collaborating closely with business stakeholders to identify impactful AI use cases.
Responsibilities
- Design, build and deploy production-ready AI applications using Large Language Models (LLMs).
- Develop Retrieval Augmented Generation (RAG) solutions and AI agents.
- Integrate AI capabilities with enterprise systems and internal data platforms.
- Build secure, scalable APIs and services using Python.
- Work closely with business stakeholders to identify and deliver high-value AI use cases.
- Evaluate and optimise model performance, accuracy, and reliability.
- Ensure solutions meet governance, security, and regulatory requirements.
Requirements
- Proven experience in Python development.
- Knowledge of Azure OpenAI and the Azure AI ecosystem.
- Experience with RAG architectures and frameworks such as LangChain or LangGraph.
- Familiarity with AI techniques for prompt engineering and LLM optimisation.
- Experience in working with vector databases and semantic search.
- Skilled in developing REST APIs and cloud-native applications.
- Familiar with Git, CI/CD, and containerisation using Docker/Kubernetes.
- Understanding of AI governance and security practices.