AI Engineer / 1

We are looking for an AI Engineer to join a project focused on building AI-powered solutions that support engineering teams in their daily development and testing activities.

You will work hands-on with LLM-based agents, agentic workflows, AI-assisted development, evaluation frameworks, and guardrails. A major area of the project is test automation, but the solutions you build will also support broader software development workflows.

You will have significant independence in designing and improving AI agents and their skills, while collaborating closely with QA/SDET and engineering teams. An important part of the role is taking a metrics-driven approach to AI quality, using evaluations and measurable results rather than relying only on subjective assessment of LLM outputs.

Your responsibilities:

• Design, develop, and maintain AI agents and subagents supporting engineering and test automation workflows.
• Build and orchestrate multi-stage agent workflows, including building, composing, analyzing, validating, and executing tasks.
• Develop reusable capabilities for agentic tooling, including documentation, helper scripts, templates, and agent skills.
• Build and maintain evaluation frameworks (evals) to measure agent quality, identify regressions, and continuously improve prompts and workflows.
• Design and implement guardrails and AI autonomy policies, including action classification such as allow / ask / deny.
• Work closely with QA/SDET teams to understand testing practices, code conventions, and API testing patterns.
• Support AI-assisted software development and test automation use cases.
• Iteratively improve AI solutions based on measurable results and feedback.
• Contribute to tooling around code generation, code understanding, and engineering knowledge.

Must have:

• Hands-on experience with OpenCode or a similar AI/agentic development environment, such as Claude, Cursor, GitHub Copilot, or comparable tooling.
• Practical experience with AI-supported software development and LLM-based solutions.
• Good knowledge of TypeScript and/or JavaScript, sufficient to understand existing code and perform code reviews.
• Understanding of software quality assurance principles.
• At least regular-level experience with test automation and/or software development.
• Ability to work independently and take ownership of solutions from initial idea through implementation and improvement.
• Strong communication skills and ability to collaborate effectively with QA/SDET and engineering teams.
• An analytical, iterative approach to assessing and improving the quality of AI solutions.

Nice to have:

• Experience with BDD testing frameworks.
• Experience with multi-agent orchestration or parallel agent workflows.
• Knowledge of code graph analysis or knowledge graph tooling.
• Experience generating code based on OpenAPI / Swagger specifications.
• Familiarity with multiple LLM providers and differences in their tool-use capabilities.
• Experience designing LLM evaluations, prompt evaluation, regression testing, or AI guardrails.
• Knowledge of CI/CD pipelines, particularly Jenkins.
• Familiarity with SBOM generation and CycloneDX.
• Previous experience within the project's industry/domain.

Hybrid work model: 3 days from the office, 2 days of home office.

Office location: Warsaw, Poznań or Lublin.

Thank you for your interest in our offer. We will contact selected candidates whose experience best matches the requirements of the role.

Additional Information

We hereby inform you that Inetum Polska sp. z o.o. has implemented an internal reporting (whistleblowing) procedure. The content of the procedure and the possibility to submit an internal report are available at:

https://inetum.whispli.com/speakup?locale=pl