> Markdown version of [/jobs/ext/1833901-postdoctoral-research-associate-machine-unlearning-and-model-editing-for-ai-biosecurity](https://www.wearedevelopers.com/jobs/ext/1833901-postdoctoral-research-associate-machine-unlearning-and-model-editing-for-ai-biosecurity). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # Postdoctoral Research Associate, Machine Unlearning and Model Editing for AI Biosecurity - **Company:** The Rector & Visitors Of The University Of Virginia - **Location:** Charlottesville, VA, United States - **Salary:** $60,000.0 - $75,000.0 - **Contract:** Temporary contract - **Skills:** Artificial Intelligence, Cyber Security, Desktop Computing, Python (Programming Language), Machine Learning, Natural Language Processing, Open Source Technology, Software Tools, Tensorflow, Software Engineering, Pytorch, Large Language Models, Information Technology, HuggingFace - **Published:** July 4, 2026 - **Apply:** https://diversityjobs.com/main/sendform/8/8/28176/1/17608286?backUrl=%2Fcareer%2F17608286%2FPostdoctoral-Research-Associate-Machine-Unlearning-Model-Editing-For-Ai-Biosecurity-Virginia-Charlottesville ## About the Role * 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, Education: Doctoral degree Experience: None Licensure: None ## Description 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., * 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, 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., 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. ## Related Videos - [Machine Learning: Promising, but Perilous](https://www.wearedevelopers.com/videos/627-machine-learning-promising-but-perilous) - [Photonic Computing: Programming a New Class of AI Accelerators (incl. Live Coding)](https://www.wearedevelopers.com/videos/100196-photonic-computing-programming-a-new-class-of-ai-accelerators-incl-live-coding) - [Machine learning in the browser with TensorFlowjs](https://www.wearedevelopers.com/videos/155-machine-learning-in-the-browser-with-tensorflowjs) - [A hundred ways to wreck your AI - the (in)security of machine learning systems](https://www.wearedevelopers.com/videos/715-a-hundred-ways-to-wreck-your-ai-the-in-security-of-machine-learning-systems) - [Geometric deep learning for drug discovery](https://www.wearedevelopers.com/videos/264-geometric-deep-learning-for-drug-discovery) - [Getting Started with Machine Learning](https://www.wearedevelopers.com/videos/260-getting-started-with-machine-learning) ## Related Articles - [How to Become an AI Engineer](https://www.wearedevelopers.com/magazine/331-how-to-become-an-ai-engineer) - [How to start an AI project for a good cause and boost your career](https://www.wearedevelopers.com/magazine/15-how-to-start-an-ai-project-for-a-good-cause-and-boost-your-career) - [Dev Digest 134 - Where pixels sing?](https://www.wearedevelopers.com/magazine/477-dev-digest-134-where-pixels-sing) - [MLOps And AI Driven Development](https://www.wearedevelopers.com/magazine/82-mlops-and-ai-driven-development) - [Coffee with Developers - Maria Apazoglou - Making AI understandable for all in production](https://www.wearedevelopers.com/magazine/475-coffee-with-developers-maria-apazoglou-making-ai-understandable-for-all-in-production) - [Got AI ideas but no money? Here are 10 free ways to level up your AI skills with Google Cloud](https://www.wearedevelopers.com/magazine/600-got-ai-ideas-but-no-money-here-are-10-free-ways-to-level-up-your-ai-skills-with-google-cloud)