AI Engineer

My client are a Series A SaaS partner, who deliver AI platforms for their customers, at scale.

They are looking for an AI Engineer who loves building reliable applications powered by large language models. This role is less about model research and more about engineering robust AI systems that work in the real world.

What you’ll be doing

• Designing and deploying production AI applications using LLMs
• Building RAG pipelines, agentic workflows, and scalable orchestration layers
• Integrating vector databases, APIs, and data pipelines
• Creating evaluation frameworks to measure system performance and reliability
• Improving AI systems through observability, feedback loops, and experimentation
• Optimising prompts, latency, cost, and output quality across different models

What we’re looking for

• Hands-on experience building applications with LLM APIs
• Practical knowledge of RAG architectures, vector databases, and prompt engineering
• Experience building multi-step AI workflows or agent systems
• Strong Python (or similar) and experience building production services
• Understanding of cloud platforms and distributed systems
• Ability to work with non-deterministic systems and iterate through experimentation

Nice to have

• Experience with AI-assisted coding tools
• Familiarity with evaluation or model observability tools
• Experience in regulated or complex enterprise environments
• Exposure to real-time systems, search technologies, or multimodal AI

Why join

• Work on real-world AI systems used by global organisations
• High-impact projects at the forefront of generative AI
• Collaborative team of AI specialists and engineers
• Competitive salary + bonus
• Learning budget and strong career growth opportunities