PNNL's National Security Directorate (NSD) is seeking an AI Assurance Researcher to address complex data and analytic challenges by understanding, exploring, and manipulating the internal mechanics and behaviors of AI models, providing insights into decision boundaries and mathematical fingerprints of data properties.
Requirements
- Familiarity with the current ML research landscape, especially xAI, adversarial machine learning, AI safety, and the science of deep learning
- Familiarity with PyTorch and other associated deep learning libraries
- Hands-on experience analyzing the internal structures of deep learning models, particularly those associated with large language models and large vision models
Responsibilities
- Design and execute machine learning (ML) experiments that follow the current best practices within the community, including large scale experiments on HPC (e.g. experiments that take a week)
- Evaluate AI systems across multiple axes, including standard performance metrics but also generalization to out-of-distribution settings
- Write high-quality research code
- Assess empirical results to guide future research and experimental steps
- Conduct work in secure environments and execute work from an operational security perspective
Other
- This position is based in either Richland, WA or Seattle, WA and requires an onsite presence.
- U.S. Citizenship
- Background Investigation: Applicants selected will be subject to a Federal background investigation and must meet eligibility requirements for access to classified matter in accordance with 10 CFR 710, Appendix B.
- Drug Testing: All Security Clearance positions are Testing Designated Positions, which means that the applicant selected for hire is subject to pre-employment drug testing, and post-employment random drug testing.
- SCI Clearance
