Architect and own our AI pipelines — from multi-agent workflows and retrieval pipelines to automatic evaluation and feedback loops.
Design scalable context generation systems that synthesize documentation, styleguides, and steering artefacts to enhance agent performance.
Optimize retrieval pipelines to achieve the ideal balance of quality, latency, and cost.
Build internal tooling for evaluation, context engineering, and inference — the backbone of how we train and measure our agents.
Collaborate across teams (PM, UX, product engineering, and leadership) to ship high-impact features at startup speed.
Define and scale the team culture — recruiting top talent, mentoring others, and embedding the principles of AI-native engineering into everything we build.
Requirements
A degree (Masters/PhD preferred) in Computer Science, Artificial Intelligence, Data Science, Applied Mathematics, or related fields.
10+ years of engineering experience, with 3+ years leading AI-focused teams.
Fluency in some of these areas: Python, Anthropic/OpenAI APIs, vector databases, and eval tooling.
Strong fundamentals in Machine Learning, Data Science and Evaluation Frameworks
Experience with agent orchestration, retrieval-augmented generation (RAG), and agentic workflows
Experience developing agentic workflows
Proven experience shipping AI-first products that bridge research and real-world application.
Comfort working across the stack or partnering closely with frontend/backend teams.
Tech Stack
Python
Benefits
25 days holiday
health insurance, including dental and vision, which extends to partners and dependents
company-matched pension
commuting stipend for those who live outside London