Applied AI Engineer

Salary: £120,000 - 140,000 per year

Requirements:

• 4+ years of experience building production software
• Experience shipping LLM-powered systems that have been used by real users
• Hands-on experience across areas such as RAG, prompting and/or agents
• Strong production engineering fundamentals, including an understanding of reliability and incident response
• Good technical understanding of LLMs, including concepts such as sampling parameters and embeddings
• Experience designing meaningful evaluations for AI/LLM systems
• Comfortable using agentic development tooling such as Claude Code, Codex or similar
• Experience working and shipping at pace
• Strong communication skills with the ability to explain technical decisions clearly and concisely

Responsibilities:

• Build, improve and maintain production LLM systems
• Improve the cost and latency of LLM-powered features without sacrificing accuracy
• Design and implement evaluation frameworks that can reliably measure whether changes genuinely improve the product
• Investigate production failures raised by analysts, identify root causes and implement effective fixes
• Work across areas including RAG, prompting and agentic systems
• Partner closely with Product to shape new functionality and take ideas through to production
• Use AI-native engineering tools such as Claude Code as part of your day-to-day development workflow
• Make sound technical decisions when working through ambiguous engineering problems

Technologies:

• AI
• Claude Code
• LLM
• RAG

More:

We are an exciting AI technology business building and improving production LLM systems. This is a hands-on engineering role focused on real-world AI problems where the technology is already being used in production. You will have the opportunity to influence how the product evolves, working closely with Product to improve quality, reduce cost and latency, build better evaluation frameworks and solve real production failures. We are based in London, Moorgate, and offer a hybrid working model with 2 days per week in the office. Our engineering environment is heavily AI-native, with tools such as Claude Code forming a key part of how we build and ship software.

last updated 39 week of 2026