Scientist I - ML/AI Regulatory Genomics and Cell Type-Targeted Tools for Brain Health

Brain Health is a new global collaborative research initiative designed to accelerate understanding of human brain diseases through large-scale human tissue analysis, open science, AI-enabled disease modeling, and translational platform technologies. Building on foundational advances in human brain cell atlases, quantitative neuropathology, single-cell and spatial biology, multimodal molecular profiling, and AI-enabled analysis, Brain Health is developing a scalable framework for understanding disease progression directly in the human brain and identifying new opportunities for therapeutic development.

This effort centers on a lab-in-the-loop AI platform that designs and validates synthetic enhancer sequences for precision cell-type targeting across the brain. We train sequence-to-function models on the Allen Institute’s cross-species whole-brain multiomic atlases, generate synthetic enhancers optimized for strength and specificity, and validate candidates in vivo with single-cell resolution across thousands of brain cell types. Thousands of enhancer AAVs have been screened in mice for functional activity using a consistent pipeline and released through the Genetic Tools Atlas. Each round of screening adds new tools and feeds back into model training, tightening the loop between computational prediction and biological discovery. Models, validated sequences, and the underlying codebase will be openly released as a platform for designing synthetic regulatory elements in any tissue or cell type.

We are seeking a Scientist I to contribute to cross-team efforts defining the regulatory biology of this platform to interpret why designed sequences succeed or fail in the intact brain and to turn each round of in-vivo validation into a tuned model. In this role you will transform cross-species single-cell multiomic atlases into training and evaluation sets, analyze whole-brain enhancer-AAV screens across thousands of cell types, and work alongside scientists and machine learning colleagues to set the design objectives and prospective success criteria for each lab-in-the-loop cycle. The ideal candidate is a regulatory genomics scientist who is fluent enough in modern sequence models to shape them, and who is motivated by the prospect of building genetic tools that reach disease-relevant cell types.

Ph.D. in genomics, computational biology, neuroscience, genetics, or a related field, or equivalent experience

Experience with single-nucleus multiomic, spatial, methylation, or 3D genome data, and with enhancer screens such as MPRA, STARR-seq, or enhancer-AAV assays

Research experience in gene regulation or regulatory genomics, including enhancers, chromatin accessibility, or transcription factor biology, with a supporting publication record

Proficiency in Python or R for large, high-dimensional biological datasets, with working familiarity with sequence-based deep learning and AI-assisted research tools

Primary work location is Seattle; any remote work must be performed in Washington State.