Responsibilities:
- Design and build systems that detect performance issues in real-time computer vision pipelines, capable of identifying degradation over time and triggering alerts.
- Develop and maintain unsupervised testing tools to validate CV pipelines both in real-time and during system rollout or retraining.
- Actively participate in brainstorming sessions and technical discussions across the ML and QA teams.
- Regularly propose improvements to team workflows, increase automation, reduce tech debt, and boost system reliability.
Requirements:
- 3+ years of experience with Python in production environments
- 3+ years of hands-on experience in data science, ideally applied to real-world ML systems
- Experience using Large Language Models (LLMs) for development, debugging, or automation tasks
- Hands-on experience with kubectl for monitoring and debugging ML systems in production
- Very good verbal and written English skills (at least B2+).
Nice to have:
- Experience in ML QA, monitoring, or model validation workflows
- Experience working with large-scale data pipelines or big data environments
- Familiarity with tools like MLflow, DVC, or other experiment/data tracking platforms