AI Engineer / 1

Description

Join a project building AI tools that help engineering teams with their daily development and testing work.

Your hands-on work will cover LLM-based agents, agentic workflows, AI-assisted development, evaluation frameworks and guardrails. Test automation is a major focus, but the tools will also serve wider software development.

You will decide much of how AI agents and their skills are designed and refined, working closely with QA/SDET and engineering staff. The approach is metrics-driven: evaluations and measured results rather than only subjective judgement of LLM output.

The company is part of a global group operating in 19 countries with over 28,000 staff, and it reported €2.5 billion in revenue in 2023. It offers digital transformation consulting, infrastructure and application management, deployment of partner solutions from Microsoft, SAP, Salesforce and ServiceNow, and custom software development. Its teams work from Warsaw, Poznań, Katowice, Lublin, Rzeszów and Łódź.

Responsibilities

• Design, build and maintain AI agents and subagents for engineering and test automation work.
• Build and orchestrate multi-stage agent workflows that cover building, composing, analysing, validating and running tasks.
• Create reusable agent tooling such as documentation, helper scripts, templates and agent skills.
• Build and maintain evals that measure agent quality, catch regressions and steadily improve prompts and workflows.
• Design and implement guardrails and AI autonomy policies, including action classes allow, ask and deny.
• Work with QA/SDET teams on testing practices, code conventions and API testing patterns.
• Support AI-assisted development and test automation use cases.
• Improve AI solutions step by step, based on measured results and feedback.
• Contribute to tooling for code generation, code understanding and engineering knowledge.

Requirements

• Hands-on experience with OpenCode or a comparable AI or agentic development tool, such as Claude, Cursor or GitHub Copilot.
• Practical work with AI-supported software development and LLM-based solutions.
• Good TypeScript and/or JavaScript skills, enough to read existing code and review it.
• Understanding of software quality assurance principles.
• At least regular-level experience in test automation and/or software development.
• Able to work independently, owning a solution from the first idea through implementation and improvement.
• Strong communication skills and effective collaboration with QA/SDET and engineering teams.
• An analytical, iterative approach to judging and raising the quality of AI solutions.
• 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 from OpenAPI / Swagger specifications.
• Familiarity with several LLM providers and how their tool-use capabilities differ.
• 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 in the project's industry or domain.

Conditions

Hybrid work: 3 days in the office and 2 days from home.

Office location: Warsaw, Poznań or Lublin.

The company operates an internal whistleblowing procedure.

Benefits

• A cafeteria system that lets you choose your benefits from a range of options.
• Referral bonuses of up to PLN6,000 for referring specialists.
• Additional revenue sharing for starting partnerships with new clients.
• Ongoing support from a dedicated Team Manager.
• Technical mentoring from an assigned technical leader, matched to your expertise and the project's needs.
• Full funding for training, certifications and technology conferences.
• A team-building budget for online and on-site events.
• Opportunities to join charitable initiatives and local sports programs.