Senior Full-Stack AI Engineer (3D) in London

As a Senior Full-Stack Engineer (3D), you will be a lead contributor in building the next generation of AI-native applications. You sit at the intersection of robust backend orchestration and intuitive frontend design. Your primary mission is to design and implement "agentic" workflows/harnesses/systems where AI doesn't just respond to prompts but proactively executes tasks, manages state, and interacts with external tools to solve complex user problems.

You will work across the entire stack, leveraging best in class frameworks and tooling for both frontend, data storage, runtime and API design. You will work closely with the UX Research team to understand and develop new interfaces and interaction techniques.

Responsibilities

• End-to-End Engineering: Lead the development of full-stack features, from database schema design to high-fidelity UI implementation.
• Agentic Workflow Orchestration: Design and implement backend logic that allows AI agents to interact with APIs, databases, and long-running processes autonomously.
• Agentic UX Design: Build "Human-in-the-loop" interfaces that allow users to monitor, steer, and collaborate with AI agents in real-time.
• Infrastructure & Security: Architect secure and performant backend systems using best practices and design patterns, to support high-concurrency AI operations.
• State Management: Manage complex, asynchronous application states where data may be updated concurrently by both users and background AI agents.
• Performance Optimization: Build efficient applications and services, understand how to best to maximize both perceived and actual user experience. Optimize the entire request-response lifecycle, focusing on minimizing latency in LLM streaming and database queries.
• Technical Health: Maintain high standards for code quality, focusing on static type safety, clean architectural consistency and comprehensive unit and integration testing.

Minimum Qualifications

• Experience: Typically 5–8 years of professional full-stack software engineering experience.
• Frontend Stack: Deep expertise in React, TypeScript, and modern CSS/HTML. Ability to build complex, data-rich applications.
• Backend Stack: Proven experience with RDBs (e.g. PostgreSQL) and Object Stores (e.g. s3).
• API Design: Strong experience designing and consuming RESTful and/or GraphQL APIs with a focus on reliability and security.
• AI Development Tooling: Expert-level proficiency with modern agentic development environments (e.g., Cursor, Claude Code, Windsurf) to accelerate the shipping cycle.
• Architecture: Solid understanding of distributed systems, serverless architectures, and relational database modeling.
• Deployment: Familiarity with CI/CD practices and tools (e.g. Jenkins) and cloud providers for compute/network (e.g. AWS ALBs/ECS).
• Communication: Ability to bridge the gap between technical LLM capabilities and practical, user-facing product features.

Preferred Qualifications

• Agentic Frameworks: Hands-on experience with agentic orchestration frameworks (e.g., LangChain, LangGraph, CrewAI, or PydanticAI).
• AI UX Patterns: Deep understanding of "Agentic UX" patterns, such as ReAct, streaming UI updates, generative UI, and proactive notifications.
• LLM Observability: Experience with monitoring and evaluation tools for AI agents (e.g., LangSmith, Braintrust, or Helicone) to track agent reliability and cost.
• Tool-Calling Expertise: Proven track record of building "Tools/Functions" for LLMs to interact with third-party SaaS platforms or internal databases.
• Durable Runtimes: Hands-on experience with durable runtime frameworks such as temporal or similar.
• Storage: Experience with Supabase e.g. Row Level Security (RLS), and database migrations.
• Vector Databases: Familiarity with pgvector or other vector stores for RAG (Retrieval-Augmented Generation) workflows.
• Real-time Systems: Experience with WebSockets or Supabase Realtime to provide instant feedback for long-running agentic tasks.