AI Harness Engineers
About The Position
Capgemini Financial Services is establishing a new AI-native product organization focused on building software products for insurance claims, payment operations, and health operations. These products are sold to banks, insurers, and health plans. The organization operates with a deliberately small, senior team, utilizing an engineering model where AI agents perform most of the implementation, guided by human engineers who author specifications, tooling, evaluation suites, and guardrails. Humans retain ownership of all consequential decisions, with certain decisions being exclusively human-led due to regulatory requirements in their domains.
Requirements
- Prior ownership of a development environment, build system, or paved-path workflow used by a multi-team engineering organization.
- Strong Python skills, with fluency in containerization and Kubernetes.
- Comfort operating CI/CD systems at scale.
- Direct experience deploying or operating AI coding agents (e.g., Claude Code, Cursor, Copilot, or in-house), beyond personal use.
- Close following of frontier agentic-systems research (harness design, reinforcement learning from execution feedback, evaluation methods) with the ability to implement them in production within a quarter.
- A measurement habit: ability to demonstrate developer-experience improvements with data.
- Daily, hands-on use of AI coding assistants as part of your own development workflow.
Nice To Haves
- Hermetic build systems (Bazel, Buck, Nix, or similar) or monorepo tooling at scale.
- Experience with Go or Rust.
- Git-at-scale experience.
- Experience building one-shot or unattended agent pipelines with hard failure caps and human escalation.
- Experience turning agent execution traces into training or evaluation datasets, or building reinforcement learning pipelines from execution feedback.
- Publicly written about developer experience or agent harnesses.
- Financial services engineering exposure (banks, insurers, or payment providers).
Responsibilities
- Own development environments end to end, ensuring they are fast, isolated, and reproducible for both human engineers and agent fleets, including sandboxes, ephemeral environments, and warm starts.
- Own deterministic CI and the pre-push validation surface to ensure failures are caught early.
- Own the agent harness, including tooling, permissions, retry limits, and orchestration blueprints for coding agents, with continuous improvement based on agent failures.
- Own the recursive improvement loop, ensuring agent transcripts, failure modes, and evaluation verdicts automatically feed back into harness changes and model adaptation datasets.
- Own evaluation-gated merges, integrating evaluation suites as a first-class merge gate in CI.
- Instrument and measure key metrics such as cold-start times, agent PR merge rates, and review-time economics to drive improvements.
Benefits
- Paid time off based on employee grade (A-F): Vacation: 12-25 days, depending on grade, Company paid holidays, Personal Days, Sick Leave
- Medical, dental, and vision coverage
- Retirement savings plans (e.g., 401(k) in the U.S., RRSP in Canada)
- Life and disability insurance
- Employee assistance programs
- Other benefits as provided by local policy and eligibility
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Senior
Education Level
No Education Listed
