Senior AI Engineer

Job Description

LONDON AI Startup:

About the role

As the company's Senior AI Engineer, the successful candidate will build the AI that makes this real. They'll be designing the agent architecture that takes messy human intent and turns it into correct, auditable action against enterprise systems of record. This is the hard, important part of the product. It's entirely theirs to own.

What they're building

Enterprise software was built to store data and enforce process. It was never built to be used by humans who have better things to do. The result: highly trained people wasting hours every day fighting screens instead of doing the actual work.

The company attacks this from three angles:

• Intent-to-action: A user describes an outcome. The company figures out which systems to touch, in which order, with which data, and executes it with the right approvals and a clean audit trail.
• Cross-system workflows: Event-driven chains that span SAP, Salesforce, and ServiceNow simultaneously. "If invoice posted AND variance >3%, draft an explanation and route for approval." Actions no single vendor would ever build.
• Computer-use for the long tail: Not every enterprise workflow has a reliable API. They use computer-use agents to automate the 30 to 40 percent of processes that live in screens, VDI sessions, and legacy thick clients.

Their goal is to become the trusted control plane for enterprise work: the place teams go to understand their systems, execute across them, and ship new workflows without waiting on IT.

What you'll work on

• Design and own the core agent architecture: how the company takes a natural language intent, decomposes it into steps, calls the right APIs and UI agents, handles failures gracefully, and closes the loop with the user
• Build reliable, production-grade LLM pipelines covering context management, tool use, structured outputs, and multi-step reasoning across systems with real enterprise data
• Create evaluation frameworks that allow the team to ship with confidence: evals, replay testing, regression detection, and output quality scoring against enterprise workflows
• Build computer-use agents that can navigate legacy enterprise UIs including SAP GUI, ServiceNow, and thick clients, reliably enough to trust in production
• Work directly with the founders and customers to understand where AI fails in real enterprise workflows and translate that into better systems
• Set the technical standards for how the company builds AI. The successful candidate will define the patterns the rest of the team builds on

Must haves

The company is looking for a formidable engineer. Someone who stops at nothing to get something working. Enterprise AI is unglamorous: the systems are ugly, the APIs are partial, the data is messy, and "it worked in the demo" is not good enough. The right candidate will actually want to solve this.

• Shipped AI-powered features that real users depend on in production, with an understanding of what breaks and how to prevent it
• Deep hands-on experience with LLM APIs, agentic patterns, and tool/function calling. Not just wrappers around OpenAI, but genuine systems-level thinking about how agents fail
• Treats reliability, latency, and cost as first-class engineering concerns, not afterthoughts
• Builds evals before shipping, not after something breaks in front of a customer
• Strong Python; comfortable owning the full loop from prompt design to deployed API
• High ownership: able to take something from an ambiguous problem statement to a clean, working solution with minimal hand-holding
• Pragmatic — startups are always on fire somewhere. The right candidate knows when to let something burn and when to drop everything

Nice to haves

(The company encourages applications even if none of these apply. They're genuinely optional.)

• Computer-use or browser automation work with tools like Playwright, browser agents, or UI parsing
• RAG over structured enterprise data (ERP schemas, CRM objects, ITSM records)
• Fine-tuning or RLHF on domain-specific tasks
• Prior founding engineer or early-stage startup experience

The team

The successful candidate will work directly with the founders from day one. No engineering manager in the way, no sprint planning theatre.