Overview
We're looking for a skilled Generative AI Engineer to help build and scale a modern AI platform within a large, complex enterprise environment. This role combines hands-on Python development with DevOps practices and the integration of large language models into secure, production-grade systems.
You'll be working on emerging technologies, solving real-world engineering challenges, and contributing to the evolution of AI capabilities in a regulated setting.
Key Responsibilities
- Design, build, and maintain backend services and APIs that provide secure access to AI capabilities
- Develop Python-based components for prompt orchestration, output validation, and evaluation workflows
- Integrate LLMs into existing enterprise systems, ensuring alignment with security and observability standards
- Implement and manage CI/CD pipelines in line with engineering best practices
- Collaborate with cross-functional teams (engineering, platform, and operations) to ensure reliable deployment and scaling
- Support experimentation, benchmarking, and cost/performance analysis of AI models
- Contribute to retrieval-augmented generation (RAG) solutions and data integration patterns
- Establish reusable API standards, frameworks, and documentation to support wider adoption
- Troubleshoot and optimise distributed systems and cloud-based services
Core Skills & Experience
- Strong background in backend engineering using Python (additional exposure to Node.js or similar is beneficial)
- Hands-on experience working with Generative AI and large language models
- Understanding of prompt engineering challenges and model evaluation techniques
- Solid DevOps capabilities, including CI/CD pipelines and monitoring practices
- Experience operating in secure, regulated environments with strict governance controls
- Proven track record of integrating AI into production applications or workflows
- Knowledge of authentication, secrets management, and secure system design
Nice to Have
- Experience with API gateways, service meshes, or GitOps tooling
- Familiarity with cloud platforms and services (compute, containers, storage, messaging)
- Experience building RESTful APIs (FastAPI or similar) and microservices architectures
- Exposure to infrastructure-as-code and automated deployment workflows
- Knowledge of prompt evaluation tooling
- Experience with both SQL and NoSQL databases
- Understanding of vector search and retrieval-based AI patterns
Ways of Working
- Takes initiative and solves problems without needing heavy direction
- Comfortable navigating ambiguity in a fast-evolving technical landscape
- Strong communicator who can work effectively across technical and non-technical teams
- Curious and proactive in exploring new AI approaches responsibly
- Focused on automation and efficiency to improve delivery
What Good Looks Like
- High-quality, secure AI services delivered into production
- Improved team productivity through automation and streamlined processes
- Reliable, observable systems with performance and evaluation built in
- Solutions that are easy for other teams to adopt and build upon
- Clear, accessible documentation supporting rapid onboarding
