Brain Regulatory Genomics Scientist I - Cell-Type Tools

Allen Institute; Seattle (WA); Hybrid; USD 87,000 - 108,000; Full time

Benefits offered by this job

Relocation assistance

Visa sponsorship

401k plan

Medical insurance

Paid time off

Job summary

Allen Institute in Washington state seeks a Scientist I to advance regulatory genomics and cell-type targeted brain tools through cross-species single-cell data and enhancer screens.

You will collaborate with ML and biological scientists to shape sequence-to-function models, define design objectives, and validate candidates in vivo, contributing to a broadly open platform for synthetic regulatory elements.

Qualifications

• Ph.D. in genomics, computational biology, neuroscience, genetics, or related field, or equivalent experience.
• Proficiency in Python or R for large, high-dimensional biological datasets; familiarity with sequence-based deep learning and AI-assisted tools.
• Experience with single-nucleus multiomic, spatial, methylation, or 3D genome data and enhancer screens.

Responsibilities

• Curate training, validation, and benchmark sets from cross-species single-nucleus multiomic data.
• Define cell-type targets and design objectives for synthetic enhancers from whole-brain single-cell atlas data.
• Apply sequence-to-function models and guided optimization to rank candidate enhancers and interpret them via motif content, syntax, and spacing.
• Plan design-and-test cycles with experimental colleagues, set success criteria, and feed results back into model training.
• Publish findings and openly release validated sequences, benchmarks, and documentation.

Skills

Python

R

sequence models

data analysis

Education

PhD in genomics / related field

Tools

Enformer

Borzoi

ChromBPNet

Job description

Allen Institute in Washington state seeks a Scientist I to advance regulatory genomics and cell-type targeted brain tools through cross-species single-cell data and enhancer screens.

You will collaborate with ML and biological scientists to shape sequence-to-function models, define design objectives, and validate candidates in vivo, contributing to a broadly open platform for synthetic regulatory elements.