Director of Machine Learning

Overview

Are you ready for new challenges and new opportunities? Join our team in Seattle!

Current job opportunities are posted here as they become available.

Director of Machine Learning — AI Powered Biological Design

The mission of the Allen Institute is to unlock the complexities of bioscience and advance our knowledge to improve human health. Using an open science, multi-scale, team-oriented approach, the Allen Institute focuses on accelerating foundational research, developing standards and models, and cultivating new ideas to make a broad, transformational impact on science.

Join our artificial intelligence powered lab, an initiative at the intersection of academic creativity and start-up style execution. Our mission is to apply machine learning to biological design. Join us as we build a series of interconnected design-test-loop “flywheels” that enable design of synthetic enhancers, protein binders, and more.

We are looking for a Head of Machine Learning to lead ML strategy and execution across three tightly integrated project teams building biological DBTL “flywheels” for AI model development. The goal of the overall program is to advance de novo biological sequence-to-function design capabilities. An initial flywheel is focused on designing regulatory elements (enhancers) that drive user-specified gene expression across all mammalian cell types.

We envision at least three flywheels operating continuously, spanning DNA, RNA, and protein design. In addition to building dedicated models for specific tasks like enhancer design, we aim over time to integrate multiple specialized models into more generalized sequence-to-function design capabilities. Situated at the interface of experimental biology and computation, you will report into the Seattle Hub for Synthetic Biology (Sea Hub) administrative unit.

You will own the ML vision and execution for this program, supervising ML/data scientists and collaborating with project team leads as we learn how to harness a portfolio of flywheels to maximally accelerate biological design.

At the Allen Institute, we believe that science is for everyone – and should be open to everyone. We are dedicated to combating biases and reducing barriers to STEM careers more broadly.

We also believe that science is better when it includes different perspectives and voices. We strive to make the Allen Institute a place where everyone feels like they belong and are empowered to do their best work in a supportive environment.

We are an equal-opportunity employer and strongly encourage people from all backgrounds to apply for our open positions.

• In partnership with the Executive Director and in collaboration with the Allen Technology Office, define and own the ML strategy for the enhancer flywheel and additional synthetic biology flywheels, including success metrics and roadmaps
• Build and manage a central ML team, plus ML/data scientists embedded in project teams
• Architect and implement sequence-to-function and generative models for regulatory element and other DNA, RNA, and protein design, leveraging state-of-the-art architectures (CNNs, transformers, diffusion, etc.)
• Design and optimize DBTL loops via collaboration with project teams, e.g., supporting assay design, active learning tactics, assay configuration, and benchmarking
• Supervise quantitative analysis and QC of high-throughput assays (e.g., MPRA, single-cell data), integrating external datasets such as scATAC-seq and RNA-seq for transfer learning
• Prioritize projects based on organizational goals, collaborating cross-functionally to ensure timely, high-quality delivery
• Establish ML best practices across projects (code quality, experiment tracking, model and data versioning, documentation, reproducibility)
• Partner with data/engineering teams in the Office of the CTO to define and maintain the computational infrastructure required for large-scale sequence modeling and genomics data integration
• Serve as the primary program ML representative, clearly communicating strategy, trade-offs, and results to project leads, leadership, and external collaborators, and contributing to publications and presentations
• Propos…