Agentic Harness Engineer
Stitch is seeking an Agentic Harness Engineer to design and implement tools that enable AI agents to function within their systems. The role focuses on creating frameworks for testing and monitoring AI agents, ensuring adherence to engineering standards, and collaborating with various teams to enhance agent performance. Ideal candidates will have over 4 years of software engineering experience and a strong understanding of best practices, along with enthusiasm for AI technologies. The position is pivotal for shaping Stitch's autonomous engineering approaches and requires a hands-on, innovative mindset.
Job description
About Stitch
Stitch is a payments infrastructure company on a mission to make it easier for enterprise businesses to connect to the financial system and build better experiences for their customers. We are expanding the team to enable Stitch to broaden our product offering and extend our geographical footprint. The Agentic Harness Engineer is a hands-on, greenfield builder responsible for designing and implementing the toolkit and infrastructure that enables AI agents to operate within Stitch’s systems. This includes building connectors to internal tooling, provisioning secure execution environments, and ensuring agents adhere to engineering standards before any human review. This is a fast-moving, autonomous contributor role — the first of its kind at Stitch — requiring a pragmatic implementer with a genuine enthusiasm for agentic engineering.
Key responsibilities
- Design and build agent harness frameworks to test, evaluate, and monitor autonomous AI agents in production and simulated environments.
- Build and maintain agent connectors to internal systems (e.g. Notion, Google Drive, codebase), managing access permissions to ensure agents operate with appropriate scope and that integrations do not decay over time.
- Develop evaluation pipelines and benchmarking systems to measure agent performance, reliability, and safety.
- Collaborate with AI/ML engineers, product teams, and platform engineers to ensure agent systems are observable, debuggable, and production-ready.
- Contribute to the engineering team through PRs, architecture discussions, and ceremonies.
- Build tooling and infrastructure to support agent orchestration, simulation environments, and automated testing of agent workflows.
- Participate in architecture design, code reviews, performance evaluation, and internal tool development for agent-based systems.
- Diagnose and troubleshoot agent failures, hallucinations, orchestration errors, and system integration issues.
- Continuously improve agent reliability, observability, and performance by developing robust evaluation harnesses and feedback loops.
Requirements
- Bachelor’s degree in Computer Science, AI, Software Engineering, or related fields.
- 4+ years experience in software engineering, preferably in full-stack or platform engineering. Note: ML engineering or LLM-training experience is not required and not the target profile for this role.
- Strong understanding of software engineering best practices, including Agile development, source control, testing frameworks, and CI/CD.
- Experience building testing frameworks, evaluation systems, or developer tooling.
- Familiarity with LLM-based systems, AI agents, or autonomous workflows.
- Genuine enthusiasm for agentic AI as the future of engineering — candidates who are ambivalent about AI-assisted development are not the right fit. Personal tinkering or side projects with AI tooling is a strong signal.
- Comfort operating as a sole contributor in a greenfield function — this role has no direct reports and no existing team or playbook to inherit. The successful candidate builds the function from scratch, reporting directly to the Engineering Lead.
Nice to haves
- Experience with AI agent frameworks.
- Experience with LLM evaluation frameworks and prompt testing.
- Knowledge of distributed systems and orchestration frameworks.
- Experience with Kubernetes and cloud infrastructure.
- Familiarity with observability tools for AI systems.
- Experience building simulation environments or synthetic test datasets.
Benefits & Perks
Remote-friendly Work
We recognise and value the importance of enabling remote work and maintaining a globally distributed workforce. We cater to equitable employee experiences for both in-office and remote team members. We remain conscientious about ensuring a level playing field, especially around team events, business meeting practices, and office-driven benefits. While we facilitate remote work, we also see the value in bringing the full team together in person from time to time.
Stock Ownership
We believe in the power of ownership. That's why every full-time team member becomes a part-owner of Stitch. Our employee stock ownership plan ensures that when the company thrives, you do too.
Time Off
Taking time off from work is critical to ensure that you can take necessary breaks and have time for important life events outside of work. It also helps you manage your energy better. In line with this, we provide a generous annual leave policy, along with supportive family responsibility, parental, study, and long-tenure sabbatical leave options, designed to accommodate the diverse needs of our team.
Learning & Development Fund
We are committed to the professional growth of our team. Each year, we allocate $3,000 per full-time team member for learning and development, supporting a culture of continuous improvement and skill enhancement.
Health Insurance Contribution
Recognising the importance of health and well-being, we contribute to health insurance for all team members and provide group health insurance schemes in certain jurisdictions.
Equipment
To ensure our team has the tools they need, new members receive a brand-new Mac laptop along with the necessary peripheral equipment upon joining Stitch.
Employee Assistance Programmes
We care about the well-being of our team. Our Employee Assistance Programmes provide you with the necessary resources and support to not only excel in your job but also to thrive in your personal life. Whether it's counselling, advice, or support services, we're here to help every step of the way.
Other notable benefits and perks
- Celebrations for important life and work milestones
- Daily team lunches in the Cape Town office
- Bi-annual work retreats
- New starter dinners
- Frequent team and company events
Compliance with POPIA Our processing of your Personal Information is subject to, and in compliance with, the provisions of POPIA. Privacy and security of your information We will process your information only on instructions from you, which we are deemed to have received when you submit information on our website. We will maintain the confidentiality and security of such information per the standards contained in the POPIA, which requires us to adopt reasonable safeguards to protect the integrity and confidentiality of such information from unauthorized access, loss or destruction. These benefits are applicable for full-time staff members but may not apply for fixed-term and part-time staff.
Job details
- Published
- July 2, 2026
- Last checked
- July 28, 2026
- Job source
- greenhouse
- Workplace
- Remote · ZA
- First seen
- July 2, 2026
See how well you match this job
Log in or sign up and Eva will compare your profile with this role, explain your strengths and show what to improve.
Sign up to see your matchAlready have an account? Log inMore at Stitch Money
Similar jobs from this company
None listed.
Across the market
Similar jobs from other companies
Third-party content disclaimer
Full job descriptions are sourced directly from third-party applicant tracking systems (ATS), job boards, recruitment platforms, and employer career pages.
LiftmyCV does not claim ownership of this content or guarantee its accuracy or current availability. All original content is the intellectual property of the respective employers or other rights holders.
LiftmyCV hiring intelligence, availability checks, and related-job recommendations are generated from LiftmyCV data and public sources.
If you prefer, you may apply directly via the original listing for transparency.