Postdoc: AI Biosecurity - Unlearning & Model Editing

University of Virginia; Charlottesville (VA); On-site; USD 60,000 - 75,000; Full time

Benefits offered by this job

UVA Health Plan

Vision Coverage

Dental Plan

Benefit Savings Plans

Life Insurance

Disability Benefits

Paid Time Off

Job summary

The University of Virginia School of Data Science seeks an accomplished researcher to develop and evaluate machine unlearning and model editing methods. You will implement, compare, and benchmark techniques that reduce hazardous biological capabilities in AI systems while preserving useful scientific functions.

Reporting to Assistant Professor Tom Hartvigsen, you will design experiments, lead the open UBS-Bio evaluation suite, contribute to interpretability studies, and publish reproducible

Qualifications

• PhD in data science, CS, ML or related field completed by hire.
• Strong Python programming and experience with ML frameworks like PyTorch and Hugging Face.
• Proven publications in ML/NLP and/or biosecurity.
• Experience training, finetuning, or post-training for large language models.
• Software engineering practices for reproducible and reusable research tools.

Responsibilities

• Implement and compare machine unlearning and model editing methods.
• Design experiments measuring safety–utility tradeoffs.
• Develop adversarial testing protocols with the lab partner.
• Lead development of the UBS-Bio evaluation suite.
• Support interpretability analyses of model representations.
• Publish manuscripts and release reproducible code.

Skills

Python

PyTorch

Hugging Face Transformers

LLM fine-tuning / post-training

Reproducible research tooling

Publications in ML/NLP/biosecurity

Education

Doctoral degree (PhD or equivalent) in data science, CS, ML or related field

Tools

Job description

The University of Virginia School of Data Science seeks an accomplished researcher to develop and evaluate machine unlearning and model editing methods. You will implement, compare, and benchmark techniques that reduce hazardous biological capabilities in AI systems while preserving useful scientific functions.

Reporting to Assistant Professor Tom Hartvigsen, you will design experiments, lead the open UBS-Bio evaluation suite, contribute to interpretability studies, and publish reproducible