Our client is an AI-native productivity startup on a mission to bring intelligence to everyday work (conversations, errands, organising and workflows) with minimal prompting. Their first product reimagines email, moving users from reading and writing messages themselves to reviewing and approving AI-completed work, with the goal of cutting average daily email time from around four hours to just thirty minutes.

The business is backed by an initial $100m investment from a profitable, internationally established parent company, and is building toward a much bigger vision: a single AI application that reduces reliance on inboxes and chat tools altogether, with agents able to plan, act, and coordinate with each other on a user's behalf

The Role

They're hiring a Full Stack Engineer (AI Systems) to build the product layer that turns these capabilities into usable, production-grade workflows. Designing how agents operate, fail, recover, and deliver consistent value to users.

What you'll do:

• Build end-to-end product features across frontend, backend, and AI integrations
• Design agent workflows that handle planning, tool use, failure, and recovery across multiple steps
• Integrate LLMs, memory, and external tools into systems that behave reliably under real-world conditions
• Design real-time AI interactions with streaming, partial results, and tight latency constraints
• Improve system reliability, observability, and fallback mechanisms
• Collaborate closely with ML, backend, and product teams to ship features end-to-end
• Iterate continuously based on real usage and failure modes

What you'll own:

• AI-native product features that move beyond chat into persistent, goal-driven workflows
• Agent workflows that reliably complete multi-step tasks across tools and sessions
• Latency and responsiveness improvements to AI interactions, without sacrificing output quality
• Robust fallback and recovery mechanisms for LLM and tool failures in production
• Patterns and abstractions for integrating LLMs, memory, and external tools into scalable systems

What They're Looking For

• Strong full-stack engineering experience (frontend + backend)
• Solid understanding of system design and API architecture
• Experience working with LLMs, RAG systems, or AI-powered applications
• Ability to handle ambiguity and make pragmatic engineering decisions
• Strong ownership — able to take features from idea to production
• Comfort working in a fast-moving environment with evolving requirements

Tech Stack

Next.js · Python · Node.js · PyTorch · OpenAI / Anthropic / open-source LLMs · SQL & NoSQL · Kubernetes · Docker

The Team

A small, high-talent-density, hands-on team that makes decisions collectively and moves fast, balancing shipping high-quality work with learning as they go. This role requires bringing structure, exercising judgement, and executing independently.

Package

Competitive base and equity

Interview Process

If there's a fit, expect 3 interviews (no more than 4), conducted virtually and/or onsite, evaluated by the technical team.