AI Scientist — Translational Drug Discovery

The Position

A healthier future. It’s what drives us to innovate. To continuously advance science and ensure everyone has access to the healthcare they need today and for generations to come. Creating a world where we all have more time with the people we love. That’s what makes us Roche.

Advances in AI, data, and computational sciences are transforming drug discovery and development. Roche’s Research and Early Development organisations at Genentech (gRED) and Pharma (pRED) have demonstrated how these technologies accelerate R&D, leveraging data and novel computational models to drive impact. Seamless data sharing and access to models across gRED and pRED are essential to maximising these opportunities. The new Computational Sciences Center of Excellence (CoE) is a strategic, unified group whose goal is to harness the transformative power of data and Artificial Intelligence (AI) to assist our scientists in both pRED and gRED to deliver more innovative and transformative medicines for patients worldwide.

Biological Research | AI Development (BRAID) is a team within AI Biology & Translation (AIBT) focused on developing state-of-the-art AI methods to solve key challenges in disease biology, target discovery, and translational research. We are seeking a Scientist/Senior Scientist with a strong foundation in computational, statistical, and data science, and a passion for translating technical advances into biological and clinical impact.

You will develop and define the specifics of modeling applications that empower our clinical trials. This role requires a deep understanding of how a model can fit into Genentech’s drug development lifecycle—including identifying users, determining data availability timelines, and understanding how decisions are made. You will work alongside clinical and translational research colleagues to ensure models directly improve their decision-making processes.

• Build New AI Models:
  Develop innovative models to enhance insights from outcome data and design interpretable ML frameworks.

• Connect Molecular and Clinical Data:
  Create models that link heterogeneous molecular and cellular data with clinical outcomes, specifically focusing on prognostic, predictive, and pharmacodynamic biomarkers.

• Master the Data:
  Integrate messy, heterogeneous data from internal and public cohorts into a unified, generalizable modeling framework.

• Influence Trial Design:
  Identify necessary data collection requirements for future trial designs to ensure modeling success.

• Deploy and Educate:
  Share and deploy these models with other computational users and clinical stakeholders to drive impact.

• Education:
  
  Ph.D. in Computer Science, Bioinformatics, Computational Biology, or a related quantitative field.

• AI/ML Expertise:
  Proven experience building machine learning and AI models from scratch.

• Biological Data Proficiency:
  Hands-on experience working with "messy" genomics data (e.g., aggregating dozens or hundreds of studies) and/or clinical datasets.

• Modern Engineering:
  Ability to effectively use agentic coding tools to improve the quality and quantity of code and modeling outputs.

• Education:
  
  Ph.D. in Computer Science, Bioinformatics, Computational Biology, or a related quantitative field

• AI/ML Expertise:
  Proven experience building machine learning and AI models from scratch.

• Biological Data Proficiency:
  Hands-on experience working with "messy" genomics data (e.g., aggregating dozens or hundreds of studies) and/or clinical datasets.

• Modern Engineering:
  Ability to effectively use agentic coding tools to improve the quality and quantity of code and modeling outputs.

• Education:
  
  Ph.D. in Computer Science, Bioinformatics, Computational Biology, or a related quantitative field + 2 years of experience building ML models and/or interpreting models for target discovery, biomarker discovery, or clinical decision making

• AI/ML Expertise:
  Proven experience building machine learning and AI models from scratch. Expertise within an area of modern machine learning research, such as graph/diffusion/transformer models, reinforcement learning, or…