AI Engineer — Series A enterprise AI startup (London)
Most AI deployments fail for the same reason: the model doesn’t know how your company actually works.
I’m hiring for an elite team solving exactly that. They build agents that learn an enterprise’s processes – ingesting knowledge bases, conversations, tickets and system logs, then producing instructions agents can execute, with confidence scoring that decides when to automate and when to hand back to a human.
This role sits on that core learning system.
What you’d actually be doing:
- Extending the core context learning library — ship with a customer first, then generalise it back into the platform
- Designing LLM-powered systems and agentic workflows from prototype to production
- Building agents that can autonomously edit and maintain large knowledge bases
- Owning the reliability layer: evals, confidence scoring, automate-vs-escalate logic
- Architecting async systems for complex AI orchestration
- Working directly with enterprise customers, not through a ticket queue
What they’re looking for:
- 3+ years professional experience, with production LLM systems you can talk through in real engineering detail
- Hands-on with agents and autonomous systems
- Genuine interest in how systems improve over time — human-in-the-loop feedback, prompt optimisation, context engineering
- Comfortable moving between a research paper and a production codebase
- Able to explain your work to engineers and customers alike
Bonus points for scaling LLM workflows to millions of requests, multi-agent systems in production, or building evaluation frameworks for enterprise deployments.
The culture: small, deeply technical team, high hiring bar, and problems that often have no known solution. Engineers are expected to bring direction, not wait for it.
#J-18808-Ljbffr…