AI Engineer

You will develop and apply LLM-based features end to end, build evaluation frameworks for prompt iteration and semantic retrieval, and optimize embeddings and vector stores. You will work directly with users to design solutions, follow LLM and applied-AI developments, and collaborate across engineering, product, and design. You will work in person from the London office five days per week.

Responsibilities

• Develop and apply LLM-based features end to end
• Build and maintain evaluation frameworks for prompt iteration and semantic retrieval
• Optimize embeddings and vector stores for performance and scalability
• Work with users to understand problems and design solutions
• Stay current with LLM and applied-AI practices
• Collaborate with engineers, product managers, and designers to develop product features

Requirements

• Engineering experience at technology and product-driven companies
• Experience shipping multi-provider LLM solutions to production
• Proficiency with LLM infrastructure platforms
• Experience designing large-context LLM systems
• Experience with RAG, knowledge graphs, hybrid search, or memory
• TypeScript
• React.js
• Node.js
• Ability to work in person from the London office

Benefits

• Equity
• Private health coverage
• Mallorca villa
• Relocation assistance