SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: CAD 150,000 - 177,000 / annual
Prenuvo is transforming healthcare from reactive sick-care to proactive health care through award-winning whole-body MRI scans (fast, safe, non-invasive) combined with cutting-edge AI. The company is advancing from task-specific models toward foundational work including pre-trained backbones, multi-task heads, and integration of clinical text and structured data.
You will independently own a model domain end-to-end within Prenuvo's AI Research organization, from problem framing through validated, production-deployed models. This is a hybrid role based in Vancouver requiring you to be technically credible enough to review model architectures, challenge assumptions, and roll up your sleeves when needed, while also building a team environment where people do their best work.
Key responsibilities include:
- Lead development of foundation models and multimodal systems for whole-body MRI, advancing self-supervised and large-scale representation learning across imaging, radiology, lab, and longitudinal data
- Own experiment design and validation study scoping for your domain, diagnosing failure modes independently
- Drive data quality, annotation criteria, and quality standards your models depend on, engaging directly with clinical framing
- Guide strategic application of generative and agentic AI, including LLM adaptation and workflow orchestration, to accelerate research and clinical workflows
- Contribute modeling approaches that others adopt and define a research roadmap advancing Prenuvo's foundation-model capabilities
- Lead clinical review for your domain, partner across clinical, annotation, and ML Engineering teams, and raise code-quality standards
- Deliver production-ready models with documented validation, clinical sign-off, and performance benchmarks, owning the technical narrative for your domain
You will work at the intersection of deep learning, medical imaging, and clinical translation, accountable for both scientific rigor and delivery. The role does not provide visa sponsorship; applicants must be legally authorized to work in Canada and must not require employer sponsorship.
Requirements:
- Strong MSc or PhD from a top-tier institution in CS, biomedical engineering, statistics, mathematics, or related field
- Minimum 4 academic or industry years of ML experience with strong publication or applied-research record including at least one first-author work
- Expert-level PyTorch and ability to write and review production-quality research code
- Demonstrated ability to own a model domain end-to-end (architecting, training, validating, deploying) and design experiments and validation studies independently
- Deep fluency in self-supervised learning: masked image modeling, contrastive learning, JEPA-style methods, knowledge distillation, and large-scale representation learning
- Strong command of modern vision and multimodal architectures: Vision Transformers, multimodal transformers, foundation models, and vision-language models
- Experience in medical image analysis (segmentation, detection, classification, biomarker extraction, longitudinal modeling) and multimodal fusion of imaging with radiology, clinical, lab, and structured patient data
- Experience applying generative and agentic AI (LLM adaptation, workflow orchestration) to healthcare or research applications
- Strong collaboration skills across ML Engineering, Product, and Clinical Ops with high standards for scientific rigor balanced against delivery speed
Nice to have:
- Experience in body composition, vascular imaging, organ segmentation, or lesion detection
- Familiarity with FDA 510(k) submission processes or predicate-based regulatory pathways
- Publications in top journals and conferences (ISMRM, NeurIPS, MICCAI, ICML, RSNA, etc.)
- Experience with interpretable AI and state-of-the-art AI methods
- Prior work in health tech or clinical AI environment
