Public summary
Seeking a Senior Machine Learning Engineer to develop advanced models for evaluating rehabilitation exercise quality from video keypoints. The role involves building generalizable deep learning solutions for real-time feedback on mobile devices, working closely with clinical experts, and owning the end-to-end pipeline from data acquisition to deployment. Candidates should have strong experience in computer vision, model optimization for edge deployment, and Python engineering.
Location and work setup
- Location
- Mainz, Wiesbaden
- Remote status
- Remote
- German requirement signal
- No German Required Detected
- Detected job language
- English
Responsibilities
Develop and deploy deep learning models for assessing movement quality from video keypoints across multiple exercises and fault classes; handle noisy inputs and low-latency edge processing on Android/iOS devices; collaborate with physiotherapists and doctors to translate clinical judgments into reliable machine learning evaluations; manage data extraction, annotation strategies, research novel approaches, implement computer vision pipelines, and evaluate both model and production performance; support body and hand tracking optimization within a data science team.
Qualifications
Proven experience building and deploying deep learning/computer vision models with end-to-end ownership; expertise in models for time-based action quality/error assessment or related fields such as surgical skill assessment or ergonomics; practical knowledge of transfer and few-shot learning for generalization; experience with model compression, quantization and pruning for edge devices; strong Python and PyTorch or TensorFlow skills adhering to clean coding and testing practices; preferred backgrounds include biomechanics, physiotherapy, training pose estimation or hand tracking models from scratch, and experience in regulated medical environments.