Advance the development of high-performance computer vision architectures to detect and diagnose medical conditions within complex radiological datasets (MRI, CT).
Design and implement rigorous validation frameworks to ensure model robustness, clinical efficacy, and compliance with medical device certification standards.
Engineer solutions with clinical trust at the core, prioritizing model interpretability and uncertainty quantification to provide actionable insights for healthcare professionals.
Optimize scalable ML pipelines within a modern Docker and AWS ecosystem, ensuring a seamless transition from experimental research to production-grade deployment.

Ph.D. or Master’s in Computer Science, Machine Learning, Engineering, Mathematics, or related quantitative field.
3+ years of industry experience specifically focused on computer vision for medical applications.
Expertise in Python and PyTorch, with a deep understanding of medical image processing techniques and data formats.
Strong theoretical and practical understanding of modern computer vision architectures for 3D image segmentation and object detection (e.g. CNNs, ViT).
Familiarity with at least two of the following areas: Self-supervised or semi-supervised learning, Computer vision foundation models, Anomaly detection, Active learning.
Proven ability to contribute to large-scale codebases and handle complex datasets in a collaborative environment.
Commitment to robust software engineering practices: including version control (Git), unit testing, CI/CD, and writing clean, maintainable code.

Use your personal benefits budget flexibly and choose the perks that suit you best!

Machine Learning Engineer

Key skills