SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Prenuvo is transforming healthcare from reactive sick-care to proactive wellness through award-winning whole-body MRI scanning combined with AI. The company integrates optimized hardware, software, and increasingly AI-driven analysis across domestic and global clinics.
You will independently own a model domain end-to-end within the AI Research organization, from problem framing through validated, production-deployed models. As Prenuvo's AI org evolves from task-specific models toward foundational work (pre-trained backbones, multi-task heads, clinical text and structured data integration), you will design experiments, diagnose failure modes independently, and shape how the team approaches entire problem classes.
Key responsibilities include:
• Lead end-to-end fine-tuning of large language models (SFT, PEFT/LoRA, DPO/RLHF) on clinical text, radiology reports, and longitudinal patient histories to build specialized, domain-adapted clinical models.
• Design, develop, and operationalize autonomous and semi-autonomous AI agent systems utilizing multi-step reasoning, tool use, workflow orchestration, planning, and memory architectures to automate complex research and clinical workflows.
• Establish robust, automated, and human-in-the-loop NLP evaluation frameworks to benchmark clinical accuracy, detect hallucinations, assess reasoning capabilities, and ensure safety, reliability, and regulatory compliance.
• Collaborate on multimodal systems connecting imaging foundation models with LLMs, structured lab data, and clinical text to create holistic patient insight platforms.
• Own experiment design and validation study scoping for your domain, diagnosing failure modes independently and establishing rigorous scientific benchmarks.
• Drive data quality standards, clinical annotation criteria, and knowledge grounding (RAG, ontology alignment) for language and agentic pipelines in close collaboration with medical experts.
• Partner across clinical, annotation, and ML Engineering teams, raising code-quality standards and contributing reusable architectures adopted org-wide.
• Deliver production-ready LLM and agentic models with documented validation, clinical sign-off, and continuous monitoring benchmarks.
You will work at the intersection of deep learning, medical imaging, and clinical translation, accountable for both scientific rigor and delivery. This is a hybrid role based in Vancouver. You must be legally authorized to work in Canada; no visa sponsorship is provided.
