Postdoctoral Research Associate, Machine Unlearning and Model Editing for AI Biosecurity

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

About The School

The University of Virginia School of Data Science, the first of its kind in the nation, advances discovery, innovation, and societal impact through collaborative, open, and responsible data science research and education. Founded in 2019, the School brings together expertise across business, computation, engineering, humanities, law, mathematics, social sciences, and statistics to address complex, real-world challenges. Its academic offerings include a B.S. in Data Science, an undergraduate minor, residential and online M.S. in Data Science programs, and a Ph.D. in Data Science, all designed to prepare students for a rapidly evolving data-driven world.

About The Position

This position develops and evaluates machine unlearning and model editing methods that selectively reduce hazardous biological capabilities in AI systems while preserving beneficial scientific functions. The researcher reports to Assistant Professor Tom Hartvigsen and will work closely with other SDS faculty members including Chirag Agarwal and Stephen Turner, and works with faculty in interpretability and with a laboratory partner that leads adversarial red teaming. The role centers on implementing, innovating, and comparing model editing and unlearning methods, measuring safety–utility tradeoffs against both benchmarks and realistic task batteries, and leading technical development of an open evaluation suite for AI biosecurity. Strong familiarity with biology and biosecurity is important, as the work targets biological capabilities and connects to a human-subjects evaluation running in parallel.

Key Responsibilities

• Implement and compare machine unlearning and model editing methods, including gradient-based fine-tuning, representation-level edits, and inference-time steering
• Design and run experiments that measure how interventions affect benchmark scores and real-world task performance, producing safety-utility curves
• Develop adversarial testing protocols with the laboratory partner, including prompt-based jailbreaks, fine-tuning recovery, and ensemble attacks
• Lead engineering of the open-source UBS-Bio evaluation suite, including baselines, metrics, and documentation
• Support interpretability analyses that identify which model representations encode hazardous versus beneficial capabilities
• Prepare and present manuscripts and publish and maintain reproducible code releases

Minimum Qualifications

• Doctoral degree (PhD or equivalent) in data science, computer science, machine learning, or a related field, completed at the time of hire
• Strong programming in Python and hands-on experience with modern ML frameworks such as PyTorch and Hugging Face Transformers
• Track record of publications in machine learning, natural language processing, and/or biosecurity
• Demonstrated experience training, finetuning, or post-training for large language models
• Software engineering practices that support reproducible and reusable research tools

Preferred Qualifications

• Understanding of biology, biosecurity, or dual-use research considerations
• Experience with machine unlearning, model editing, or related capability-mitigation methods
• Experience with mechanistic interpretability or representation analysis
• Familiarity with adversarial robustness, red-teaming, or jailbreak evaluation
• Experience releasing and maintaining open-source ML evaluation tooling
• Familiarity with secure computing environments and controlled-access model arrangements

Anticipated Salary: $60,000 - $75,000 per year

Anticipated Start Date: September 1, 2026

Health And Other Benefits

(visit Health and Other Benefits for additional information)

• UVA Health Plan: the choice between 3 different health plans
• Vision Coverage
• Dental Plan
• Benefit Savings Plans
• Life Insurance
• Disability Benefits
• Paid Time Off: starting with 22 days of time off per year, 12 or more holidays, 8 weeks parental leave

Education Benefits (visit Education Benefits For Additional Information)

After six months of employment, full-time and part-time (20+ hours) employees in a benefits-eligible position are offered options of:

• Use of up to $5250 per calendar year towards a for-credit degree program or for-credit certificate program
• Use of up to $2000 of the total $5250 noted above per calendar year for professional development including job-related training, conferences, and initial certificate exams.

Position Details

This position will remain open until it is filled. This is a full-time in-person position at the School of Data Science at the University of Virginia in Charlottesville, VA. The initial appointment is for one year; however, the appointment may be renewed for an additional year contingent upon funding and satisfactory performance. This is an exempt level, term-limited (restricted), benefited position.

Application Process

Please apply online, and search for R0084978.

Complete An Application Online And Attach

• Cover letter detailing your interest and relevant experience to this position
• Resume or CV
• Two letters of recommendation with contact information

Applications that do not contain all required documents will not receive full consideration.

Internal applicants: Search and apply for jobs on the UVA Internal Careers website.

References will be completed via direct reach. Please plan to provide at least three references when applying.

A background check is required and will be conducted per university policy prior to the first day of employment.

For questions about the position, contact Associate Professor Stephen D. Turner at [e-mail].

For questions about the application process, please contact Daniel Strong, Senior Human Resources Recruiter, at [e-mail].

For more information about UVA and the Charlottesville community, see www.virginia.edu/life/charlottesville and https://embarkcva.com/.

The University of Virginia is an equal opportunity employer. All interested persons are encouraged to apply, including veterans and individuals with disabilities.

Minimum Requirements

Education: Doctoral degree

Experience: None

Licensure: None

PHYSICAL DEMANDS

This is primarily a sedentary job involving extensive use of desktop computers. The job does occasionally require traveling some distance to attend meetings and programs.

The University of Virginia is an equal opportunity employer. All interested persons are encouraged to apply, including veterans and individuals with disabilities. Learn more about UVA’s commitment to non-discrimination and equal opportunity employment.