At Roche you can show up as yourself, embraced for the unique qualities you bring. Our culture encourages personal expression, open dialogue, and genuine connections, where you are valued, accepted and respected for who you are, allowing you to thrive both personally and professionally. This is how we aim to prevent, stop and cure diseases and ensure everyone has access to healthcare today and for generations to come. Join Roche, where every voice matters.
Primary Purpose of Job (Job Summary)
This role is responsible for developing and validating algorithm models based on radiomics, clinical data, and Multimodal Large Language Models (LLMs) to support scientific clinical research. By collaborating with oncology experts and hospitals, the position drives the innovative application of Generative AI, Large Language Models (LLMs), and domain-specific AI in tumor diagnosis, treatment recommendation, and prognosis evaluation.
Principle Roles & Responsibilities / Accountabilities
- Collaborate with oncology experts and hospitals to collect, process, and analyze multimodal medical imaging data (e.g., CT, MRI, PET-CT) and clinical data for building high-quality radiomics models.
- LLM Application Development: Design and implement clinical decision support tools based on RAG (Retrieval-Augmented Generation) or Fine-tuning techniques.
- Design and implement algorithm development and validation pipelines to ensure scientific rigor and regulatory compliance.
- Algorithm Pipelines: Design and implement algorithm development and validation pipelines (including LLM evaluation) to ensure scientific rigor and regulatory compliance.
- Coordinate cross-functional teams to deploy algorithms in clinical settings.
- Stay updated on global trends in radiomics and explore innovative applications of AI/ML in precision oncology.
- Prepare technical documentation and research papers, and present findings at academic conferences to enhance the Medical Department's algorithmic leadership in research collaborations.
Qualification and Experience
Education/Qualifications
1. Master’s degree or above in Medical Imaging, Biomedical Engineering, Computer Science, Data Science, or related fields.
2. AI Expertise: Experience in radiomics or medical AI algorithm development is preferred; hands-on experience with LLM/LMM development (e.g., Transformer, Prompt Engineering) is a strong plus.
3. > 3 years’ experience in medical affairs or technical project management in multinational company
Job Required Competencies
1. Technical Stack: Proficient in Python/PyTorch; familiarity with LLM frameworks (e.g., LangChain, HuggingFace) and medical imaging tools (ITK-SNAP).
2. Knowledge of oncology clinical research workflows and data standards (e.g., GCP, DICOM).
3. Strong cross-functional collaboration skills to work with medical experts, engineers, and regulatory teams.
4. Prior publications in radiomics-related journals/conferences (e.g., RSNA, MICCAI) is a plus.
5. Deep understanding of AI ethics, data privacy, and regulatory requirements in healthcare.
Travel Frequency
25% - 50%
A healthier future drives us to innovate. Together, more than 100’000 employees across the globe are dedicated to advance science, ensuring everyone has access to healthcare today and for generations to come. Our efforts result in more than 26 million people treated with our medicines and over 30 billion tests conducted using our Diagnostics products. We empower each other to explore new possibilities, foster creativity, and keep our ambitions high, so we can deliver life-changing healthcare solutions that make a global impact.
Let’s build a healthier future, together.
Roche is an Equal Opportunity Employer.