backend ai developer (f/m/x).

• Design, build and maintain backend services and APIs using Java and Quarkus.
• Use AI tools such as GitLab Duo and Claude Code as part of your daily workflow to accelerate
coding, testing, debugging and code review.
• Solve day-to-day backend team tasks – features, bug fixes, refactors, integrations – leveraging AI
to move faster without compromising quality.
• Write automated tests (unit and integration) for backend services, using AI to speed up test
creation and improve coverage.
• Take part in code reviews – both AI-assisted and with teammates – ensuring code quality and
adherence to our engineering standards.
• Troubleshoot and resolve issues in CI/CD pipelines, using GitLab Duo to speed up root-cause
analysis.
• Collaborate closely with other backend engineers, QA and product to deliver reliable, well-tested
software.

• 4+ years of hands-on experience in backend development
• Experience with Java. (Quarkus is a plus)
• Practical experience using AI-assisted development tools such as GitHub Copilot, GitLab Duo,
Claude Code, or similar as part of a daily engineering workflow.
• Experience designing and building APIs and Java-based microservices that run reliably at scale
in production.
• Experience writing automated unit and integration tests for backend systems.
• Ability to understand the functional and business context of a feature before designing the
technical solution.
• Curiosity and willingness to experiment with new AI tools and integrate them responsibly into
day-to-day development practices.
• Comfortable working in a fast-moving environment where AI-assisted development practices
are still evolving.
• Strong attention to detail, critical thinking, and problem-solving skills.
• Good verbal and written communication skills in English.
• Collaborative, adaptable, and able to manage multiple priorities effectively

Nice to Have
• Experience with LLM-based integrations, Retrieval-Augmented Generation (RAG), or agent
orchestration workflows.
• Familiarity with MCP (Model Context Protocol) or similar tool/context integrations that connect
AI assistants to internal systems.
• Exposure to AI-native development practices beyond code completion, such as spec-driven
development frameworks, custom prompt or skill libraries, and automation workflows.