Role Title: Predictive Modeling Contractor (RDE 9 / DAISAE)
Target Workstream: RDE 9 / RDE 9B2 (DAISAE Platform & Predictive Modeling Subteams)
Preferred Location: South San Francisco (SSF), CA; open to Basel, Switzerland or remote depending on candidate fit
Duration: November 1, 2026 – December 31, 2027 (approx. 14 months)
Approved Budget: CHF120,000 for remainder of 2026 / CHF250,000 for 2027
We are seeking a contractor with a background combining AI rapid prototyping and Predictive Modeling to support the DAISAE platform and predictive analytics subteams within the RDE 9 program. This role focuses on co-developing shared data and technical foundations (e.g. Ontologies, Knowledge Graphs), prototyping agentic AI capabilities, and advancing predictive models for drug safety risk prediction across the product lifecycle.
AI Prototyping & MCP Tool Development: Rapidly explore, evaluate, and prototype emerging AI tools and agentic capabilities, specifically developing MCP tools and AI agent integrations for DAISAE.
Predictive Modeling: Build and refine predictive models using multi-modal datasets (including in vitro, in vivo, omics, clinical trial data, real-world data (RWD), and spontaneous safety reports) to enable risk prediction from early molecule-level evaluation to late-stage and post-marketing patient safety.
Architecture & Platform Design: Translate feasibility findings and prototype evaluations into concrete architectural design and platform requirements for shared data and technical foundations.
Co-Development & Governance Collaboration: Work in an agile way to prototype reusable technical capabilities before transitioning components to RDT (Roche Digital Tech) for formal validation, compliance, and production rollout.
Cross-Functional Alignment: Collaborate with data scientists, safety scientists, and RDT technical partners to ensure technical execution aligns with business priorities.
Education: MSc or PhD in Data Science, Computer Science, Computational Biology, Bioinformatics, Biostatistics, Epidemiology, or a related quantitative field.
Technical Expertise:
Strong expertise in predictive modeling, machine learning, and AI prototyping.
Hands-on experience developing agentic AI systems, LLM tools, and MCP tools.
Proficiency in handling biomedical datasets (omics, clinical trials, RWD, or in vitro/in vivo data).
Agile prototyping mindset with software engineering skills tailored for data science.
Domain Knowledge:
Background in pharmacovigilance, drug safety, toxicology, or quantitative risk management is highly desirable.
Soft Skills:
"AI native" approach to problem-solving with adaptability to fast-moving frameworks.
Proactive attitude and strong communication skills suitable for global matrix team settings.
