Responsibilities:
- Design and implement pipelines for detecting various types of events in video streams.
- Develop and maintain an internal SDK for solving similar computer vision tasks across projects.
- Actively participate in brainstorming sessions and technical discussions.
- Regularly propose ideas to improve team workflows, reduce tech debt, and make our daily work easier and more effective.
Requirements:
- 3+ years of hands-on experience with Python.
- 3+ years of experience in Computer Vision.
- Practical experience with PyTorch and/or TensorFlow.
- Strong understanding of model training, evaluation, and optimization.
- Comfort with daily use of LLM-based tools (e.g., for code generation, debugging, or documentation).
- 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 working with video-based CV tasks (e.g., multi-frame tracking, action recognition, temporal models).
- Familiarity with deployment pipelines and SDK development for ML/CV.
- Background in working with real-world noisy data.