Senior Applied AI Engineer (LLM)

Location: London, UK; hybrid working approach

Company

Insurtech software business developing B2B and B2B2C platforms that use data and technology to improve life and protection insurance underwriting.

What you will do

• Design, experiment with, and deploy production LLM-based and agentic systems for extracting and reasoning over medical records and application data.
• Build and maintain evaluation harnesses to measure whether model and prompt changes improve system performance.
• Architect multi-step, tool-using workflows with explicit state, guardrails, and human-in-the-loop review where required.
• Develop language understanding, extraction, and reasoning capabilities using advanced LLM and agentic techniques.
• Collaborate with Product, Design, and Underwriting SMEs to align ML capabilities with product goals and domain constraints.
• Take systems from prototype to production while optimizing latency, cost per run, reliability, and scalability.

Requirements

• 6+ years of experience in ML/AI, with deep hands-on expertise in NLP, LLMs/SLMs, and agentic systems.
• Hands-on experience building with OpenAI and Anthropic models and APIs, plus strong knowledge of LLMs and agent architectures.
• Practical experience with LiteLLM, vLLM, and Langfuse or equivalent LLM observability tooling.
• Proven ability to design, build, and own evaluation harnesses for LLM and agent outputs.
• Proven ability to design and optimize prompts and context, including few-shot, chain-of-thought, and prompt-tuning techniques, using measurable evaluation.
• Strong Python skills; experience with FastAPI for service development and Postgres or similar databases for data persistence.
• Comfort with event-driven and asynchronous architectures.
• Working knowledge of PyTorch or TensorFlow, Docker, Kubernetes, and cloud platforms; AWS is preferred.
• Ability to focus on business and underwriting outcomes, challenge specifications, propose alternative approaches, and own features through production impact.
• Entrepreneurial, ownership-driven, action-oriented mindset with a Build Fast, Fail Fast approach in agile, iterative environments.

Nice to have

• Experience with Claude Code, Codex, and associated coding-agent workflows.
• Prior experience with DSPy, GEPA, or similar prompt and context optimization approaches.

Culture & Benefits

• Hybrid working approach supporting work-life balance.
• Continuous learning and development opportunities, team-building days, social activities, and wellbeing initiatives.
• 25 days of annual leave with the option to buy or sell additional days.
• Private health insurance for employees and dependents, optical benefits, group life insurance, and income protection.
• 15% combined employee and employer retirement contributions, subsidized gym membership, and an Employee Assistance Program.
• Enhanced parental leave, adoption and fertility leave, volunteering time off, charitable donation matching, and cycle-to-work and electric-car salary-sacrifice schemes.