Scientist I: ML/AI for Synthetic Brain Enhancer Design

Allen Institute; Washington (District of Columbia); Hybrid; USD 87,000 - 108,000; Full time

Benefits offered by this job

Relocation assistance

Visa sponsorship

Job summary

The Allen Institute is seeking a Scientist I to build the computational backbone of a lab-in-the-loop platform that designs and validates synthetic enhancers for brain cell-type targeting. You will scale model training on cloud GPUs and curate large multi-omic datasets to inform new designs, contributing to open-source code and community tools.

You will collaborate with researchers to advance regulatory genomics, share models, sequences, and code openly, and help ensure accessibility and

Qualifications

• Ph.D. in computer science, computational biology, bioinformatics, engineering, or related field or equivalent experience.
• Strong software engineering in Python with reproducible environments.
• Experience training deep learning models with PyTorch, JAX, or TensorFlow on multi-GPU or distributed infra.
• Experience building data pipelines for large scientific datasets that do not fit in memory.
• Familiarity with foundation models, transformer architectures, and large language models.
• Ability to work independently and in a collaborative, fast-paced team environment.

Responsibilities

• Build open-source codebase for training, fine-tuning, and serving genomic sequence models.
• Train large-scale whole-brain models in multi-GPU cloud environments.
• Convert cross-species multi-omic data into reproducible training sets.
• Implement active-learning loops feeding results back into models.
• Publish findings in peer-reviewed journals and conferences.

Skills

Python

PyTorch

JAX

TensorFlow

Education

PhD or equivalent

Tools

Docker

Singularity/Apptainer

Nextflow

Snakemake

Job description

The Allen Institute is seeking a Scientist I to build the computational backbone of a lab-in-the-loop platform that designs and validates synthetic enhancers for brain cell-type targeting. You will scale model training on cloud GPUs and curate large multi-omic datasets to inform new designs, contributing to open-source code and community tools.

You will collaborate with researchers to advance regulatory genomics, share models, sequences, and code openly, and help ensure accessibility and