Senior Data Scientist III- AI Assurance Researcher

Pacific Northwest National Laboratory•Richland, WA

151d•Onsite

About The Position

PNNL is seeking a Senior Data Scientist - AI Assurance Researcher who has experience in understanding, exploring, and manipulating the internal mechanics and behaviors of AI models can provides valuable insights into the decision boundaries and mathematical fingerprints of data properties. The selected candidate should have extensive experience training models, accessing and working with data embeddings, the ability to derive theoretical queries from empirical results, and demonstrate the capacity to translate research papers and findings into mission relevant insights and tools. Key Responsibilities: Defines and leads research agendas in areas such as explainable AI, adversarial machine learning, AI safety, and the science of deep learning. Designs and executes rigorous ML experiments at scale, including large-scale training and evaluation on HPC infrastructure. Develops novel evaluation methodologies that go beyond standard performance metrics to assess generalization, robustness, and out-of-distribution behavior. Analyzes the internal structures and representations of deep learning models, with emphasis on large language models and large vision models. Interprets empirical results to identify promising research directions and guide strategic investment of team resources. Establishes best practices for research code quality, reproducibility, and integration into operational pipelines. Mentors junior researchers and engineers, fostering a culture of scientific rigor and collaborative inquiry. Conducts work in secure environments with adherence to operational security requirements. This position is based in either Richland, WA or Seattle, WA and requires an onsite presence.

Requirements

BS/BA and 5+ years of relevant work experience -OR- MS/MA and 3+ years of relevant work experience -OR- PhD with 1+ year of relevant experience
U.S. Citizenship
Ability to obtain and maintain a federal security clearance.
Must be able to demonstrate non-use of illegal drugs, including marijuana, for the 12 consecutive months preceding completion of the requisite Questionnaire for National Security Positions (QNSP).
Must pass a drug test prior to commencing employment.
Must successfully complete the applicable tier of federal background investigation post hire and receive a favorable federal adjudication.
Must disclose any affiliation with the government of a country DOE has identified as a “country of risk” and either recuse oneself or receive approval from DOE and Battelle prior to employment.

Nice To Haves

Advanced degree in computer science, engineering, mathematics, or a related field.
Deep familiarity with the current ML research landscape, particularly in explainable AI, adversarial machine learning, AI safety, and the science of deep learning.
Track record of peer-reviewed publications or technical contributions in relevant research areas.
Hands-on experience analyzing the internal structures and representations of deep learning models, particularly large language models and large vision models.
Strong proficiency in PyTorch and associated deep learning libraries.
Experience designing and executing large-scale experiments on HPC systems.
Demonstrated ability to translate research prototypes into deployable tools and capabilities.
Excellent communication skills, with the ability to convey complex research findings to both technical and non-technical audiences.

Responsibilities

Defines and leads research agendas in areas such as explainable AI, adversarial machine learning, AI safety, and the science of deep learning.
Designs and executes rigorous ML experiments at scale, including large-scale training and evaluation on HPC infrastructure.
Develops novel evaluation methodologies that go beyond standard performance metrics to assess generalization, robustness, and out-of-distribution behavior.
Analyzes the internal structures and representations of deep learning models, with emphasis on large language models and large vision models.
Interprets empirical results to identify promising research directions and guide strategic investment of team resources.
Establishes best practices for research code quality, reproducibility, and integration into operational pipelines.
Mentors junior researchers and engineers, fostering a culture of scientific rigor and collaborative inquiry.
Conducts work in secure environments with adherence to operational security requirements.