AI Harness Engineer: Build Self-Improving AI Pipelines

Capgemini; England; Hybrid; GBP 70,000 - 110,000; Full time

Benefits offered by this job

Disability Confident Employer

Job summary

Capgemini is hiring for an AI infra engineer who will own the end-to-end development environment for both human engineers and AI agents. You will enhance CI surfaces, improve the agent harness, and shape the feedback loop from transcripts to model updates.

The role emphasizes building hermetic build systems, handling large-scale CI/CD, and operating AI coding agents in financial services contexts. A hybrid UK-based role with global platform responsibilities.

Qualifications

• Strong Python plus container and Kubernetes fluency.
• Comfort operating CI/CD systems at scale.
• Experience deploying or operating AI coding agents.
• Familiarity with agent harnesses and evaluation methods.

Responsibilities

• Own the development environment end to end for human engineers and agent fleets.
• Maintain deterministic CI and pre-push validation surfaces.
• Develop and improve the agent harness, including permissions and retry limits.
• Oversee the recursive improvement loop with transcripts and evaluation verdicts.
• Contribute to evaluation-gated merges and measurement of pipeline performance.

Job description

Capgemini is hiring for an AI infra engineer who will own the end-to-end development environment for both human engineers and AI agents. You will enhance CI surfaces, improve the agent harness, and shape the feedback loop from transcripts to model updates.

The role emphasizes building hermetic build systems, handling large-scale CI/CD, and operating AI coding agents in financial services contexts. A hybrid UK-based role with global platform responsibilities.