Machine Learning Scientist

Nucs AI is revolutionizing cancer care through cutting-edge AI and medical imaging technology. Founded in 2024, the company focuses on developing AI-powered tools for oncology diagnostics and treatment planning, partnering with leading medical institutions worldwide.

Location: Remote

Responsibilities

• Develop novel ML/DL methods for medical image analysis, including segmentation, lesion detection, longitudinal tracking, treatment response prediction, and outcome modeling
• Design and conduct experiments to evaluate new approaches against clinical baselines and state-of-the-art methods
• Stay current with the literature and propose research directions that advance Nucs AI’s product and scientific goals
• Publish findings in top-tier venues (MICCAI, RSNA, JNM, Medical Image Analysis) and represent Nucs AI at scientific conferences
• Collaborate with clinicians and medical physicists to ensure methods are grounded in clinical reality
• Produce validated research outputs with documented performance benchmarks and clear handoff specifications for production engineering
• Contribute to clinical validation studies and evidence generation for regulatory submissions
• Collaborate with external academic research partners on joint studies
• Support scientific diligence with pharma and clinical partners
• Contribute to Nucs AI's scientific credibility in the field

Requirements

• PhD in machine learning, computer vision, medical image analysis, biomedical engineering, or related field
• Strong publication record in relevant venues (medical imaging, clinical ML, computer vision)
• Experience structuring and executing research collaborations with academic and clinical institutions
• Deep expertise in deep learning architectures for image analysis (CNNs, transformers, U-Nets, etc.)
• Strong programming skills in Python and deep learning frameworks (PyTorch preferred)
• Experience working with medical imaging data (PET/CT, MRI, or similar modalities)
• Strong statistical foundations - experimental design, hypothesis testing, survival analysis, and clinical biostatistics