Job description

Overview At PNNL, our core capabilities are divided among major departments that we refer to as Directorates within the Lab, focused on a specific area of scientific research or other function, with its own leadership team and dedicated budget. Our Science & Technology directorates include National Security, Integrated Discovery Sciences, and Energy and Environment. In addition, we have an Environmental Molecular Sciences Laboratory, a Department of Energy, Office of Science user facility housed on the PNNL campus. The National Security Directorate (NSD) drives science-based, mission-focused solutions to take on complex, real-world threats to our nation and the world. The AI and Data Analytics Division, part of NSD, combines profound domain expertise and creative integration of advanced hardware and software to deliver computational solutions that address complex data and analytic challenges. Working in multidisciplinary teams, we connect foundational research to engineering to operations, providing the tools to innovate quickly and field results faster. Our strengths are integrated across the data analytics lifecycle, from data acquisition and management to analysis and decision support. Read more about the AI & Data Analytics division: pnnl.gov Responsibilities As a Data Scientist in the AI and Data Analytics Division, you will work with experienced technical staff to design and implement evaluation studies, prepare mission-representative test data and scenarios, develop evaluation components and agentic harnesses, execute controlled experiments, and analyze model behavior. The work extends beyond aggregate benchmark scores to examine individual cases, meaningful data slices, component interactions, system performance under realistic operating conditions, and more. Depending on project needs, research may also address explainable AI, interpretability, or targeted mechanistic-interpretability questions. Key Responsibilities: • Implement defined test and evaluation activities for AI/ML with particular focus on pretrained transformer-based foundation models, including large language models (LLMs), vision-language models (VLMs), and the AI agents and systems that use them. • Prepare evaluation datasets, prompts, mission scenarios, meaningful data slices, test cases, scoring rubrics, and deterministic baselines. • Develop evaluation environments, test harnesses, and agentic harnesses used to exercise models, tools, retrieval systems, and end-to-end workflows. • Execute controlled experiments at the model, component, workflow, and system levels. • Analyze model behavior to identify capabilities, systematic weaknesses, failure modes, and sensitivity to data characteristics, retrieval results, tools, and operating conditions. • Examine agent trajectories, intermediate decisions, tool calls, retrieved evidence, memory or state, error propagation, recovery behavior, and points of human intervention. • Evaluate performance using aggregate metrics together with case-level analysis, behavioral categories, robustness testing, calibration and uncertainty characterization, and adversarial or off-nominal scenarios. • Evaluate hybrid systems that combine generative AI with deterministic NLP, computer vision, retrieval, search, rules, or classical machine-learning methods. • Help develop and validate automated or model-based graders against human judgments and mission-relevant criteria. • Apply functional explainability, model probing, or selected interpretability methods for understanding model and system behavior. • Document evaluation methods, assumptions, results, uncertainties, and limitations in reproducible code, visualizations, technical reports, and briefings. • Contribute technical material, data, figures, demonstrations, or preliminary results to proposals and sponsor engagements. Work Location & Requirements: • This position is based in Richland, WA or Seattle, WA and requires an onsite presence. • This position requires the ability to obtain and maintain a federal security clearance. (see below for details) Qualifications Minimum Qualifications: • BS/BA and 2 years of data science experience -OR- • MS/MA -OR- • PhD • Experience developing or evaluating LLMs, VLMs, pretrained transformer models, AI agents, or integrated AI systems. • Experience using Python and machine-learning frameworks. Preferred Qualifications: • Experience building evaluation datasets, test harnesses, agentic harnesses, automated graders, behavioral tests, or analysis pipelines. • Experience analyzing model behavior, failure modes, robustness, calibration, uncertainty, or performance across meaningful data slices. • Familiarity with agent orchestration frameworks such as LangGraph or similar technologies involving routing, retrieval, tools, memory, state, and human oversight. • Experience with deterministic NLP, computer vision, retrieval, search, rules, or classical machine-learning methods that complement generative AI. • Experience in one or more related areas such as explainable AI, model probing, mechanistic interpretability, AI security, red teaming, uncertainty quantification, or privacy-preserving AI. • Experience contributing to applied research through technical reports, publications, prototypes, or open-source software. • Prior experience supporting government, national security, or other high-consequence applications. • Active TS/SCI clearance. Hazardous Working Conditions/Environment • Travel may be required for project events. Additional Information This position requires the ability to obtain and maintain a federal security clearance. A security clearance background investigation includes review of your employment, education, financial, and criminal history, as well as interviews with you and your personal references, neighbors, and co-workers to determine trustworthiness, reliability, and loyalty to the United States. The investigation also examines your foreign connections, drug and alcohol use, foreign influence, and overall conduct. Requirements: • 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. In addition, applicants 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). Note: Applicants will be considered ineligible for security clearance processing by the U.S. Department of Energy if non-use of illegal drugs, including marijuana, for 12 months cannot be demonstrated. Testing Designated Position This position is a Testing Designated Position (TDP). The candidate selected for this position will be subject to pre-employment and random drug testing for illegal drugs, including marijuana, consistent with the Controlled Substances Act and the PNNL Workplace Substance Abuse Program. About PNNL Pacific Northwest National Laboratory (PNNL) is a world-class research institution powered by a highly educated, diverse workforce committed to the values of Integrity, Creativity, Collaboration, Impact, and Courage. Every year, scores of dynamic, driven people come to PNNL to work with renowned researchers on meaningful science, innovations and outcomes for the U.S. Department of Energy and other sponsors; here is your chance to be one of them! At PNNL, you will find an exciting research environment and excellent benefits including health insurance, and flexible work schedules. PNNL is located in eastern Washington State—the dry side of Washington known for its stellar outdoor recreation and affordable cost of living. The Lab’s campus is only a 45-minute flight (or ~3 hour drive) from Seattle or Portland, and is serviced by the convenient PSC airport, connected to 8 major hubs. Commitment to Excellence and Equal Employment Opportunity Our laboratory is committed to fostering a work environment where all individuals are treated with fairness and respect while solving critical challenges in fundamental sciences, national security, and energy resiliency. We are an Equal Employment Opportunity employer. Pacific Northwest National Laboratory (PNNL) is an Equal Opportunity Employer. PNNL considers all applicants for employment without regard to race, religion, color, sex, national origin, age, disability, genetic information (including family medical history), protected veteran status, and any other status or characteristic protected by federal, state, and/or local laws. We are committed to providing reasonable accommodations for individuals with disabilities and disabled veterans in our job application procedures and in employment. If you need assistance or an accommodation due to a disability, contact us at careers@pnnl.gov . Drug Free Workplace PNNL is committed to a drug-free workplace supported by Workplace Substance Abuse Program (WSAP) and complies with federal laws prohibiting the possession and use of illegal drugs. If you are offered employment at PNNL, you must pass a drug test prior to commencing employment. PNNL complies with federal law regarding illegal drug use. Under federal law, marijuana remains an illegal drug. If you test positive for any illegal controlled substance, including marijuana, your offer of employment will be withdrawn. Security, Credentialing, and Eligibility Requirements As a national laboratory, PNNL is responsible for adhering to the Homeland Security Presidential Directive 12 (HSPD-12) and Department of Energy (DOE) Order 473.1A, which require new employees to obtain and maintain a HSPD-12 Personal Identify Verification (PIV) Credential. To obtain this credential, new employees must successfully complete the applicable tier of federal background investigation post hire and receive a favorable federal adjudication. The tier of federal background investigation will be determined by job duties and national security or public trust responsibilities associated with the job. All tiers of investigation include a declaration of illegal drug activities, including use, supply, possession, or manufacture within the last 1 to 7 years (depending on the applicable tier of investigation). Illegal drug activities include marijuana and cannabis derivatives, which are still considered illegal under federal law, regardless of state laws. For foreign national candidates: If you have not resided in the U.S. for three consecutive years, you are not eligible for the PIV credential and instead will need to obtain a favorable Local Site Specific Only (LSSO) Federal risk determination to maintain employment. Once you meet the three-year residency requirement thereafter, you will be required to obtain a PIV credential to maintain employment. The tier of federal background investigation required to obtain the PIV credential will be determined by job duties at the time you become eligible for the PIV credential. Mandatory Requirements Please be aware that the Department of Energy (DOE) prohibits DOE employees and contractors from having any affiliation with the foreign government of a country DOE has identified as a “country of risk” without explicit approval by DOE and Battelle. If you are offered a position at PNNL and currently have any affiliation with the government of one of these countries, you will be required to disclose this information and recuse yourself of that affiliation or receive approval from DOE and Battelle prior to your first day of employment. Rockstar Rewards Employees and their families are offered medical insurance, dental insurance, vision insurance, robust telehealth care options, several mental health benefits, free wellness coaching, health savings account, flexible spending accounts, basic life insurance, disability insurance*, employee assistance program, business travel insurance, tuition assistance, relocation, backup childcare, legal benefits, supplemental parental bonding leave, surrogacy and adoption assistance, and fertility support. Employees are automatically enrolled in our company-funded pension plan* and may enroll in our 401 (k) savings plan with company match*. Employees may accrue up to 120 vacation hours per year and may receive ten paid holidays per year. * Research Associates excluded. **All benefits are dependent upon eligibility. Click Here For Rockstar Rewards Notice to Applicants PNNL lists the full pay range for the position in the job posting. Starting pay is calculated from the minimum of the pay range and actual placement in the range is determined based on an individual’s relevant job-related skills, qualifications, and experience. This approach is applicable to all positions, with the exception of positions governed by collective bargaining agreements and certain limited-term positions which have specific pay rules. As part of our commitment to fair compensation practices, we do not ask for or consider current or past salaries in making compensation offers at hire. Instead, our compensation offers are determined by the specific requirements of the position, prevailing market trends, applicable collective bargaining agreements, pay equity for the position type, and individual qualifications and skills relevant to the performance of the position. Minimum Salary USD $114,000.00/Yr. Maximum Salary USD $182,100.00/Yr.

Requirements

Must-haves

The National Security Directorate (NSD) drives science-based, mission-focused solutions to take on complex, real-world threats to our nation and the world.
Prepare evaluation datasets, prompts, mission scenarios, meaningful data slices, test cases, scoring rubrics, and deterministic baselines.
Develop evaluation environments, test harnesses, and agentic harnesses used to exercise models, tools, retrieval systems, and end-to-end workflows.
Execute controlled experiments at the model, component, workflow, and system levels.
Analyze model behavior to identify capabilities, systematic weaknesses, failure modes, and sensitivity to data characteristics, retrieval results, tools, and operating conditions.
Examine agent trajectories, intermediate decisions, tool calls, retrieved evidence, memory or state, error propagation, recovery behavior, and points of human intervention.
Evaluate performance using aggregate metrics together with case-level analysis, behavioral categories, robustness testing, calibration and uncertainty characterization, and adversarial or off-nominal scenarios.
Evaluate hybrid systems that combine generative AI with deterministic NLP, computer vision, retrieval, search, rules, or classical machine-learning methods.
Help develop and validate automated or model-based graders against human judgments and mission-relevant criteria.
Apply functional explainability, model probing, or selected interpretability methods for understanding model and system behavior.
Document evaluation methods, assumptions, results, uncertainties, and limitations in reproducible code, visualizations, technical reports, and briefings.
Contribute technical material, data, figures, demonstrations, or preliminary results to proposals and sponsor engagements.
This position requires the ability to obtain and maintain a federal security clearance. (see below for details)

Nice-to-haves

Experience building evaluation datasets, test harnesses, agentic harnesses, automated graders, behavioral tests, or analysis pipelines.
Experience analyzing model behavior, failure modes, robustness, calibration, uncertainty, or performance across meaningful data slices.
Familiarity with agent orchestration frameworks such as LangGraph or similar technologies involving routing, retrieval, tools, memory, state, and human oversight.
Experience with deterministic NLP, computer vision, retrieval, search, rules, or classical machine-learning methods that complement generative AI.
Experience in one or more related areas such as explainable AI, model probing, mechanistic interpretability, AI security, red teaming, uncertainty quantification, or privacy-preserving AI.
Experience contributing to applied research through technical reports, publications, prototypes, or open-source software.
Prior experience supporting government, national security, or other high-consequence applications.
Active TS/SCI clearance.
Hazardous Working Conditions/Environment
Additional Information
This position requires the ability to obtain and maintain a federal security clearance.

Application prep

Use the role’s language and application details while tailoring your materials.

Keywords to mirror

aimlpython

Platform: jibe
Effort: medium

Benefits

Benefits detected in the listing.

Health Insurance

Dental

Vision

Wellness