ML/AI Scientist: Synthetic Brain Enhancer (Remote)

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

Benefits offered by this job

Relocation assistance

Visa sponsorship

Job summary

The Allen Institute seeks a Scientist I to build the computational backbone of a lab-in-the-loop platform that designs synthetic enhancers for brain targeting. You will scale training across cloud GPUs, curate large-scale cross-species data, and contribute to an open-source codebase for training, fine-tuning, evaluating, and running inference on genomic sequence-to-function models.

Ideal candidates are strong scientific software engineers and ML practitioners who share their models, sequences,

Qualifications

• PhD in computer science, computational biology, or related field; or equivalent experience
• Strong Python software engineering practices (version control, testing, reproducible envs)
• Experience training deep learning models with PyTorch, JAX, or TensorFlow on multi-GPU or distributed infra
• Experience building data pipelines for large scientific datasets
• Familiarity with foundation models, transformers, and LLMs
• Proven ability to work independently and in a fast-paced, collaborative team environment

Responsibilities

• Build and maintain open-source code for genomic sequence models and benchmarks
• Train large-scale whole-brain models efficiently in multi-GPU cloud environments
• Turn cross-species multi-omic data into reproducible training sets
• Implement active-learning loops feeding in vivo data into models
• Publish findings in peer-reviewed journals and conferences

Skills

Python

PyTorch

JAX

TensorFlow

Data pipelines

Multi-GPU training

Cloud GPUs

Foundation models

Collaboration

Education

PhD in CS/Computational Biology

Tools

Docker

Singularity/Apptainer

Nextflow

Snakemake

Weights & Biases

MLflow

Job description

The Allen Institute seeks a Scientist I to build the computational backbone of a lab-in-the-loop platform that designs synthetic enhancers for brain targeting. You will scale training across cloud GPUs, curate large-scale cross-species data, and contribute to an open-source codebase for training, fine-tuning, evaluating, and running inference on genomic sequence-to-function models.

Ideal candidates are strong scientific software engineers and ML practitioners who share their models, sequences,