AI Harness Engineers

Choosing Capgemini means choosing a company where you will be empowered to shape your career in the way you’d like, where you’ll be supported and inspired by a collaborative community of colleagues around the world, and where you’ll be able to reimagine what’s possible. Join us and help the world’s leading organizations unlock the value of technology and build a more sustainable, more inclusive world.

Job Description -

About us
[NewCo] is a new AI-native product organisation within Capgemini Financial Services. We build products, not projects: software for insurance claims, payment operations, and health operations, sold to banks, insurers, and health plans. Three product lines run on one shared platform, built by a deliberately small, senior team. Our engineering model is agentic: engineers author the specifications, tooling, evaluation suites, and guardrails, and AI agents do most of the implementation. Humans own every consequential decision, and in our regulated domains some decisions are human-only by design.

The role

Our engineering model depends on infrastructure most companies treat as an afterthought. AI agents implement most of our code, which means the development loop (environments, builds, CI, the harnesses agents run in) is the engine of the whole organisation's velocity. Every minute an engineer or an agent waits on an environment, a flaky test, or an unreviewable diff is product not shipped. You will own that loop end to end, for people and for agents. The harness is a self-improving system: every failure, transcript, and evaluation verdict is fuel for the next version of the harness and, increasingly, for the models inside it.

What you will own

• Development environments end to end: fast, isolated, reproducible, for human engineers and for agent fleets, including sandboxes, ephemeral environments, and warm starts.
• Deterministic CI and the pre-push validation surface, so failures are caught at the desk, not in the pipeline.
• The agent harness: the tooling, permissions, retry limits, and orchestration blueprints our coding agents operate within, improved permanently every time an agent fails.
• The recursive improvement loop: agent transcripts, failure modes, and evaluation verdicts flow back into harness changes and model adaptation datasets automatically, so the system that builds our products improves itself.
• Evaluation-gated merges: the CI integration that makes eval suites a first-class merge gate.
• Measurement: cold-start times, agent PR merge rates, and review-time economics; you improve what you instrument.

What you will need

• Prior ownership of a development environment, build system, or paved-path workflow used by a multi-team engineering organization
• Strong Python plus container and Kubernetes fluency; comfort operating CI/CD systems at scale
• Direct experience deploying or operating AI coding agents (Claude Code, Cursor, Copilot, or in-house), beyond personal use
• You follow frontier agentic-systems research (harness design, reinforcement learning from execution feedback, evaluation methods) closely enough to put it into production within the quarter it lands
• A measurement habit: you can show numbers for a developer-experience improvement you shipped
• Daily, hands-on use of AI coding assistants as part of your own development workflow

What sets you apart

• Hermetic build systems (Bazel, Buck, Nix, or similar) or monorepo tooling at scale
• Go or Rust; Git-at-scale experience
• You have built one-shot or unattended agent pipelines with hard failure caps and human escalation
• You have turned agent execution traces into training or evaluation datasets, or built reinforcement learning pipelines from execution feedback
• You have written publicly about developer experience or agent harnesses
• Financial services engineering exposure (banks, insurers, or payment providers)

The reference stack

The reference technology stack for this role is our supported paved road: self-hosted LangSmith and Lang Graph Platform as the agent runtime and evaluation plane, model providers behind a swappable gateway seam, PostgreSQL with pgvector plus Click House and S3-compatible object storage as the data platform, Neo4j Enterprise as the semantic knowledge graph, an agent memory plane serving episodic and precedent memory over MCP, MCP-native connectors, OpenTelemetry and Grafana for observability, all on CNCF-conformant Kubernetes with Helm and Argo CD, deployable to any hyperscaler or on-prem. A tool-for-tool match is not expected: analogous experience counts fully. If you have built and operated systems of this shape on comparable components (a different orchestration framework, graph engine, evaluation platform, or serving stack), you have what we are looking for.

How we work

Engineers write specs, harnesses, evals, and guardrails; AI agents execute the implementation loops. Review, not typing, is where engineering judgment goes.
Three human gates govern everything we ship: spec approval, merge, and release. Regulated code paths (money movement, authentication, cryptography, secrets) are always human-owned.
Small and senior by design. No separate QA function, no scrum masters; quality comes.

Success in year one

Fresh environment cold-start is measured in seconds, for humans and agents, and you can prove it
Agent-written PRs merge at a rising rate with flat or falling human review minutes per feature
Every recurring agent failure mode from the last two quarters has a permanent harness fix, and the harness has also lost components that model progress made unnecessary

The base compensation range for this role in the posted location is: 150000- 170000

Capgemini provides compensation range information in accordance with applicable national, state, provincial, and local pay transparency laws. The base compensation range listed for this position reflects the minimum and maximum target compensation Capgemini, in good faith, believes it may pay for the role at the time of this posting. This range may be subject to change as permitted by law.

The actual compensation offered to any candidate may fall outside of the posted range and will be determined based on multiple factors legally permitted in the applicable jurisdiction.

These may include, but are not limited to: Geographic location, Education and qualifications, Certifications and licenses, Relevant experience and skills, Seniority and performance, Market and business consideration, Internal pay equity.

It is not typical for candidates to be hired at or near the top of the posted compensation range.

In addition to base salary, this role may be eligible for additional compensation such as variable incentives, bonuses, or commissions, depending on the position and applicable laws.

Capgemini offers a comprehensive, non-negotiable benefits package to all regular, full-time employees. In the U.S. and Canada, available benefits are determined by local policy and eligibility and may include: 

• Paid time off based on employee grade (A-F), defined by policy: Vacation: 12-25 days, depending on grade, Company paid holidays, Personal Days, Sick Leave

• Medical, dental, and vision coverage (or provincial healthcare coordination in Canada)
• 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

Important Notice: Compensation (including bonuses, commissions, or other forms of incentive pay) is not considered earned, vested, or payable until it becomes due under the terms of applicable plans or agreements and is subject to Capgemini’s discretion, consistent with applicable laws. The Company reserves the right to amend or withdraw compensation programs at any time, within the limits of applicable legislation.

Disclaimers

Capgemini is an Equal Opportunity Employer encouraging inclusion in the workplace. Capgemini also participates in the Partnership Accreditation in Indigenous Relations (PAIR) program which supports meaningful engagement with Indigenous communities across Canada by promoting fairness, accessibility, inclusion and respect. We value the rich cultural heritage and contributions of Indigenous Peoples and actively work to create a welcoming and respectful environment. All qualified applicants will receive consideration for employment without regard to race, national origin, gender identity/expression, age, religion, disability, sexual orientation, genetics, veteran status, marital status or any other characteristic protected by law.

This is a general description of the Duties, Responsibilities and Qualifications required for this position. Physical, mental, sensory or environmental demands may be referenced in an attempt to communicate the manner in which this position traditionally is performed. Whenever necessary to provide individuals with disabilities an equal employment opportunity, Capgemini will consider reasonable accommodations that might involve varying job requirements and/or changing the way this job is performed, provided that such accommodation does not pose an undue hardship. Capgemini is committed to providing reasonable accommodation during our recruitment process. If you need assistance or accommodation, please reach out to your recruiting contact.

Please be aware that Capgemini may capture your image (video or screenshot) during the interview process and that image may be used for verification, including during the hiring and onboarding process.

Click the following link for more information on your rights as an Applicant in the United States.

Capgemini is a global business and technology transformation partner, helping organizations to accelerate their dual transition to a digital and sustainable world, while creating tangible impact for enterprises and society. It is a responsible and diverse group of 340,000 team members in more than 50 countries. With its strong over 55-year heritage, Capgemini is trusted by its clients to unlock the value of technology to address the entire breadth of their business needs. It delivers end-to-end services and solutions leveraging strengths from strategy and design to engineering, all fueled by its market leading capabilities in AI, generative AI, cloud and data, combined with its deep industry expertise and partner ecosystem.