AI Engineer (up to £130k)

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

Job summary

Dex, a partner to leading financial institutions, is hiring for an AI infra role focused on production agent reliability. You will own the evals, feedback loops, prompt engineering, and human-in-the-loop logic for high-stakes agent actions, while working across the full tech stack including Node and TypeScript.

You should bring production experience with agentic/LLM infrastructure and a pragmatic ML foundation, thriving in a fast-paced startup environment where data strategy evolves rapidly.

Qualifications

• Production experience building agentic or LLM infrastructure (evals, feedback loops, prompt engineering, fallbacks).
• Pragmatic ML foundation across supervised and self-supervised methods.
• Product-minded and full-stack; comfortable contributing to a Node/TypeScript stack.
• Strong system design skills; adaptable in a fast-paced assessment environment.

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

Agent infra

Human-in-the-loop

Node

TypeScript

ML foundations

Startup dynamics

Tools

Node.js

TypeScript

Job description

This role is with one of Dex's trusted partner companies. We work closely with their teams to truly understand their culture, goals, and what they're looking for, so we can match you with the right opportunity and give you context about the role before you commit to a process.

The role

This company builds and licenses AI agents that automate critical customer lifecycle workflows for major financial institutions. They run real agentic systems in production, tackling long, high-stakes banking processes. Backed by leading VCs, they're scaling rapidly with significant traction.

This is not a siloed research role. You will own the infrastructure that keeps these production agents reliable: the evals, feedback loops, prompt engineering, and fallbacks. You'll also design the human-in-the-loop logic, deciding when an agent acts and when a person steps in. It's a product-leaning seat, blending AI engineering with pragmatic ML, building across the full agentic and software stack.

The work

• 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.

What You Bring

• Production experience building and maintaining agentic or LLM infrastructure: evals, feedback loops, prompt engineering, fallbacks, and human-in-the-loop decision logic.
• A pragmatic ML foundation across supervised and self-supervised methods.
• Product-leaning and full-stack in mindset; comfortable contributing to a Node and TypeScript software stack.
• Strong system design capabilities, with proven adaptability in a technical assessment (e.g., TypeScript).
• Thrives in a fast-paced startup environment, executing at pace and owning your lane while data strategy evolves.