About the role
Ensure AI systems behave reliably in production — designing evaluation frameworks and monitoring AI output quality at scale.
Traditional QA doesn't map cleanly to probabilistic AI systems. You'll build the testing tooling, metrics, and processes that give TechNext and its clients real confidence in every deployment.
You'll work alongside AI engineers and context engineers to define what "good" means, and then prove it.
What we're looking for
- QA or SRE background with at least one production system
- Familiarity with Python testing tools and CI
- Willingness to learn the LLM eval landscape (Ragas, LangSmith, custom suites)