"Job Description
What We’re Looking For
- Proven experience in designing and building scalable, reliable, and maintainable
software systems.
- Strong proficiency in modern software development (e.g., React.js, TypeScript,
Node.js) and a deep understanding of browser architecture.
- Build LLM workflows using RAG, tool calling, structured outputs, agents, and
human-in-the-loop patterns.
Build evaluation pipelines using golden datasets, regression tests,
deterministic evaluators, and LLM-as-a-judge.
Implement observability, monitoring, guardrails, fallbacks, and validation for
reliable AI systems.
Balance model quality, latency, reliability, maintainability, and cost.
- Maintain automated tests, CI/CD pipelines, and technical documentation.
Hands-on experience with quality engineering practices, including automated
testing (unit, integration, E2E) and test automation frameworks.
Solid grasp of CI/CD, infrastructure concepts, and agile engineering practices.
- Strong troubleshooting and debugging skills, with an ability to analyze complex
system behaviors and logs.
- Excellent communication skills to explain technical trade-offs and quality standards
to diverse stakeholders.