Postdoc Investigator: Open-Language Models for Brain Biology

The Allen Institute for Artificial Intelligence; Seattle (WA); On-site; USD 135,700 - 183,598; Full time

Benefits offered by this job

Medical, dental, vision coverage

HSA/FSA and health plan options

401k plan

Commuting stipend $125 per month

Fitness and wellbeing stipend $200 per

Paid time off: 10 sick days, 7Personal

20 vacation days

12 paid holidays

Annual bonuses

Job summary

The Allen Institute for Artificial Intelligence seeks a Postdoctoral Young Investigator to advance CellOLMo, a collaboration between Ai2's ML researchers and Allen Institute scientists. You will design experiments combining single-cell data with text and reproduce methods like scGPT, Geneformer, and CellWhisperer.

You will work with Ai2 and the Allen Institute, access open language models and substantial GPU compute, and contribute to releasing models, code, and research artifacts openly.

Qualifications

• PhD completed or expected within one year in a quantitative field.
• Hands-on experience training or fine-tuning transformer-based language models.
• Strong Python and PyTorch skills.
• Experience writing reliable, reproducible research code.
• Ability to carry out independent research and communicate across ML and biology disciplines.

Responsibilities

• Design careful experiments and analyze results.
• Collaborate with researchers across ML and biology.
• Release data, code, and model weights for open science.
• Publish results and prepare for publication.
• Work with Ai2 and Allen Institute researchers to interpret results.

Skills

Python

PyTorch

Transformer models

Research coding

Independent research

Clear communication

Education

PhD in ML/Computational biology/Computational neuroscience/Physics or related

Tools

Python

PyTorch

Job description

The Allen Institute for Artificial Intelligence seeks a Postdoctoral Young Investigator to advance CellOLMo, a collaboration between Ai2's ML researchers and Allen Institute scientists. You will design experiments combining single-cell data with text and reproduce methods like scGPT, Geneformer, and CellWhisperer.

You will work with Ai2 and the Allen Institute, access open language models and substantial GPU compute, and contribute to releasing models, code, and research artifacts openly.