OVERVIEW

Read the entire description before applying. MUST HAVE: Familiarity with toolkits such as MONAI, nnUNet, ITK-SNAP, MedSAM, 3D Slicer
Are you passionate about machine learning and medical imaging? Do you want to apply your technical skills to projects that matter – like improving pediatric brain health? We are hiring a full-time Technical Research Assistant to join our collaborative team working at the cutting edge of artificial intelligence and medical imaging.
This is an ideal opportunity for graduate students, recent grads, or students completing a practicum, thesis, or capstone project, looking to gain hands-on experience in applied machine learning in healthcare. You’ll work with large, real-world imaging datasets and contribute directly to building and evaluating deep learning models with real clinical impact.

REQUIRED SKILLS & BACKGROUND

• Bachelor’s degree in Computer Science, Biomedical Engineering, Physics, or related field (Graduate students encouraged to apply)
• Proficiency in Python and deep learning frameworks (especially PyTorch)
• Strong grasp of machine learning fundamentals, particularly in classification and segmentation
• Experience working with 2D or 3D imaging data (MRI, CT, etc.)
• Familiarity with toolkits such as MONAI, nnUNet, ITK-SNAP, MedSAM, 3D Slicer
• Understanding of common model evaluation metrics (e.g., AUROC, Dice, NSD)
• Experience using Git, UNIX systems, and Jupyter notebooks
• Strong analytical thinking, independence, and attention to reproducibility

APPLICATION REQUIREMENTS

• Resume/CV
• Brief cover letter outlining technical experience and interest in the position
• Unofficial transcript
• GitHub portfolio, code samples, or publications (optional but encouraged)
  About Us
  M31 is a multidisciplinary AI and health research team working with Canada’s top hospitals and academic centers, working on projects that bridge cutting-edge machine learning with urgent clinical needs.
  Job Types: Full-time, Internship / Co-op
  Contract length: 12 months
  Pay: $35.00-$45.00 per hour
  Expected hours: 40 per week

Benefits:

• Flexible schedule
• Work from home

Work Location: Hybrid remote in Toronto, ON M5S 1A

• Preprocess and clean multi-institutional MRI, CT, and angiography datasets (de-identification, normalization, reformatting)
• Generate segmentation masks in collaboration with radiologists and clinical domain experts using tools like MedSAM and ITK-SNAP
• Implement and evaluate classification models using MONAI to predict clinical outcomes (e.g., recurrence risk)
• Build end-to-end segmentation pipelines with nnUNet for identifying key regions of interest
• Conduct model validation (internal, cross-site, and external testing) using standard metrics like AUROC, Dice, NSD, sensitivity/specificity
• Maintain reproducible workflows and clean, well-documented codebases using Git, Jupyter, and UNIX-based tools
• Collaborate closely with AI scientists, clinicians, and imaging experts across a high-performing interdisciplinary team