AI Agent Reliability Engineer

Dex; Greater London; On-site; GBP 80,000 - 120,000; Full time

Job summary

Dex partners with a leading AI-enabled fintech supplier to deliver production-grade agentic systems for major financial institutions. The role focuses on ensuring reliability and scalability of production agents across evals, feedback loops, prompt engineering, and fallbacks.

You will design human-in-the-loop logic and own the integration across the full agentic and software stack, blending AI engineering with pragmatic ML using Node.js and TypeScript.

Qualifications

• Experience with agentic/LLM infrastructure including evals, feedback loops, prompts.
• Strong ML background in supervised and self-supervised methods.
• Hands-on with Node.js and TypeScript; full-stack mindset.
• Excellent system design skills and ability to work in fast-paced environments.
• Comfort adapting as data strategy evolves in a startup context.

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

LLM infra

Prompt engineering

Feedback loops

Human-in-the-loop

ML foundations

System design

Startup mindset

Tools

Node.js

TypeScript

Job description

Dex partners with a leading AI-enabled fintech supplier to deliver production-grade agentic systems for major financial institutions. The role focuses on ensuring reliability and scalability of production agents across evals, feedback loops, prompt engineering, and fallbacks.

You will design human-in-the-loop logic and own the integration across the full agentic and software stack, blending AI engineering with pragmatic ML using Node.js and TypeScript.