Advisor, Federated Learning Data Scientist

Role Summary

Advisor, Federated Learning Data Scientist with a leadership role focusing on building large-scale, privacy-preserving models using federated learning. Responsible for identifying, assessing, and implementing algorithmic solutions that leverage diverse datasets while ensuring data privacy and security. Requires knowledge in drug development and data science to advance pipelines and develop advanced foundational models.

Responsibilities

• Foundation Model Architecture: Design and develop novel deep learning architectures for large-scale, federated pre-training on distributed data.
• Semi-Supervised & Self-Supervised Learning: Implement and advance semi-supervised and self-supervised learning algorithms tailored for federated learning.
• Federated Optimization & Aggregation: Develop robust, communication-efficient federated aggregation strategies for large, complex models with non-IID data.
• Downstream Task Adaptation: Create protocols for fine-tuning and adapting pre-trained federated models for various downstream tasks while maintaining privacy.
• Data Curation & Simulation: Establish pipelines for accessing and simulating distributed datasets; develop simulation environments to test strategies before deployment.
• Scalability and Performance: Optimize memory, latency, and communication costs to scale training and inference across many clients.
• Scientific Dissemination: Publish high-impact research and present findings to internal and external audiences.
• Code & Model Governance: Write clean, reproducible code; manage version control for data, code, and models.
• Cross-Functional Collaboration: Work with engineers, MLOps, privacy experts, and domain scientists to translate research into practical solutions.
• Literature Review & Innovation: Stay current with federated learning and deep learning advancements to drive strategy.

Qualifications

• PhD in Biostatistics, Statistics, Machine Learning, Computational Biology, Computational Chemistry, Physics, Applied Mathematics, or related field.
• Minimum of 2 years of experience in the biopharmaceutical industry or related fields, with demonstrated expertise in drug discovery and early development.

Additional Preferences

• Experience developing statistical and ML models for complex endpoints.
• Broad understanding of emerging scientific and technical breakthroughs.
• Exceptional interpersonal and communication skills; ability to navigate complex relationships.
• Strong problem-solving, analytical, and project management skills; highly self-motivated and organized.
• Ability to influence across disciplines; learning agility and portfolio-minded thinking.
• Independent, self-starter; site-based role in Indianapolis (preferred), San Francisco, or Boston with relocation provided.