Postdoctoral Research Associate, Machine Unlearning and Model Editing for AI Biosecurity 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 PlansLife 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 sdt5z@virginia.edu. For questions about the application process, please contact Daniel Strong, Senior Human Resources Recruiter, at das6zb@virginia.edu. For more information about UVA and the Charlottesville community, please 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.
