Production AI Engineer, Agentic Systems

Dex; Greater London; On-site; GBP 90,000 - 150,000; Full time

Job summary

Dex is helping you explore a high-impact AI engineering role with a trusted partner company that builds and licenses AI agents for major financial institutions. You will own the infrastructure that keeps production agents reliable, including evals, feedback loops, prompt engineering, fallbacks, and human-in-the-loop decision logic.

This product-leaning role covers the full stack, from ML models to Node and TypeScript, with fast-paced startup dynamics and opportunities to shape data strategy in a

Qualifications

• Production experience building agentic/LLM infrastructure (evals, feedback loops, prompt engineering, fallbacks).
• Pragmatic ML foundation across supervised and self-supervised methods.
• Product-leaning and full-stack mindset; comfortable with Node/TypeScript stack.
• Strong system design capabilities and ability to adapt in a fast-paced startup.

Responsibilities

• Design and implement agent reliability infrastructure, including evals, feedback loops, prompt engineering, and fallbacks.
• Build and maintain human-in-the-loop decision logic for high-stakes agent actions.
• Take ownership of proprietary supervised and self-supervised ML models, applying recent academic work pragmatically.
• Contribute across the full agentic and software stack, including Node and TypeScript.
• Shape the evolving data strategy for production AI agents in a rapidly growing environment.

Skills

Agentic infrastructure

Prompt engineering

Evals & feedback loops

Human-in-the-loop design

Full-stack mindset

Node

TypeScript

System design

Startup environment

Tools

Node.js

TypeScript

Job description

Dex is helping you explore a high-impact AI engineering role with a trusted partner company that builds and licenses AI agents for major financial institutions. You will own the infrastructure that keeps production agents reliable, including evals, feedback loops, prompt engineering, fallbacks, and human-in-the-loop decision logic.

This product-leaning role covers the full stack, from ML models to Node and TypeScript, with fast-paced startup dynamics and opportunities to shape data strategy in a