DescriptionABOUT THE POSITIONSafeFleet is shifting to AI-native engineering - Spec-Driven Development, AI-assisted implementation. We're looking for an AI-Native Quality Engineer to bridge traditional test automation with this shift: building agents that generate automation, not just writing automation by hand.
This is a hands-on engineering role. You'll build on existing LLM platforms (e.g., Claude), write and integrate automation into CI/CD, and make sure agent-generated tests are actually correct.
ESSENTIAL DUTIES & RESPONSIBILITIES- Design, develop, and maintain automated test suites (UI and API) within an AI-native test automation framework
- Build agents and AI Skills that generate and maintain automation from specs and requirements
- Analyze specs, define test strategies, and identify where agent-generated automation can be trusted versus reviewed
- Integrate automated tests - traditional and agent-generated - into CI/CD pipelines
- Ensure automation frameworks follow best practices: modularity, reusability, robust reporting
- Troubleshoot and resolve testing challenges independently, providing proactive solutions
- Document automation processes and present results to stakeholders
- Implement cost-control, latency optimization, and retry-logic strategies for production-grade agentic pipelines.
- Ensure the Framework Evolution in terms of transition of our testing ecosystem toward modular, self-healing frameworks that utilize LLM APIs and UI for automated maintenance
Salary: $100,000 - $110,000/yr CAD + 12.5% BonusThe final offer will be determined based on a combination of factors including skills, experience, and alignment with the role's responsibilities.
- Candidates at the lower end of the range will meet the core qualifications and demonstrate strong potential to grow within the role.
- Mid-range offers reflect a solid match with the role's technical and collaborative requirements.
- Offers at the top of the range are reserved for candidates who bring exceptional qualifications, specialized expertise, or unique value that significantly exceeds the baseline expectations
Requirements- 3+ years of hands-on experience in test automation
- Practical experience with LLM API integration and prompt engineering
- Skills in agentic workflows and orchestration or Familiarity with agentic concepts and workflows; interest or practical experience in orchestrating LLM-based tasks
- Capability to handle LLM limitations, including latency, cost control, and retries/fallbacks
- Familiarity with Anthropic Claude; experience with MCP is a plus
- Working knowledge of CI/CD tooling (e.g., Jenkins, Azure DevOps, GitLab)
- Advanced English communication skills
Nice to Have- Experience with Jira, Confluence, and GitHub-based workflows; Atlassian Rovo experience is a plus
- Prior experience in a "hybrid QA + systems" role - writing the test and defending why it's the right test
- Claude code courses completed
