Early Career Data Scientist 1 - Statistics

at Pacific Northwest National Laboratory in Boise, Idaho, United States

Overview

Protecting U.S. residents and visitors is among our nation's highest priorities. As adversaries gain access to sophisticated technologies and materials, the threats grow more dynamic and complex-from cyber and nuclear to chemical and biological weapons of mass effect and other forms of terrorism. The PNNL national security mission employs our researchers, tools, and technologies to play a key role in advancing the ability to identify and secure nuclear materials, detect weapons of mass effect, manage nonproliferation treaties, secure our nation's borders, and protect critical infrastructures. PNNL's scientific discovery and capabilities-rooted in innovative theory, methods, algorithms, and tools-are enabling stronger, more resilient technologies and systems to safeguard national security. Coupled with decades of radiological and nuclear materials expertise, advanced computing and threat analysis capabilities, and a broad fundamental science base, we are identifying and countering emerging threats that have significant impact at home and around the globe.

The Math, Stats, and Data Science (MSDS) Group within the National Security Directorate is looking for an early-career scientist with a background in mathematics, statistics, data science, and domain science to contribute to interdisciplinary projects in environment, materials science, energy, and national security.

Data scientists in the MSDS group use mathematics, statistics, and data analysis techniques to develop high quality and defensible methods and tools to address critical scientific challenges in national security, energy, environment, materials sciences, and fundamental sciences. In many cases, our research is deployed across a variety of compute architectures to support big data analytics problems. Examples of our capability areas include:

+ Mathematics and Statistics: We rely on deep technical expertise in classical mathematics, statistics, and computational modeling to identify, develop, and defend algorithmic solutions to challenging scientific problems. This spans a wide variety of disciplines including experimental design, optimization, uncertainty quantification, signal processing, functional analysis, modeling, artificial intelligence, machine/deep learning, game theory, graph theory, and Bayesian modeling. We also have deep expertise in bringing the areas of topology, algebra, and geometry to bear on data science problems. Recognizing that no one tool or model can provide the whole solution, we work together to produce innovative solutions that go beyond what we can do ourselves.

+ Domain Science Driven Solutions: We pride ourselves on choosing the right solution for the problem at hand. This is only possible through close partnerships with domain science experts including biologists, chemists, computer vision experts, geospatial analysts, nuclear chemists and engineers, material scientists, environmental scientists, and natural language processors. Our team understands that domain-specific characteristics should steer solutions-we guide experimental design and study planning, data collection, developing methods and executing analyses, reporting results and providing recommendations, and establishing data archival procedures. Our integral role in developing and executing study lifecycles results in explainable, reproducible, and validated research across the entire breadth of laboratory research including problems in critical-infrastructure analysis, classification of multi-omic functionality, environmental planning, nuclear safety, and national security.

+ Uncertainty, Risk, and Tradeoffs Analysis: We develop and deploy operational decision-making tools in several domains using model-based and data-driven learning. In doing so, we characterize operations, risk, resilience, and deterrence; incorporate adversarial behavior; and optimize solutions under limited resource constraints. We consider real-world uncertainties around supply chains and concepts of operations, imperfect measurements and observations, human intervention, and external impacts. In the face of these challenges, we provide strategic options and alternatives, quantify confidence in our recommendations to manage risks, and provide effective and achievable solutions that support operational objectives.

+ Deployment to Users: At our core, we are applied researchers and provide results and tools to stakeholders including Data Scientists, subject matter experts, decision, and policy makers. We serve diverse communities and work to communicate effectively by facilitating educational courses, producing high quality papers for peer reviewed publication, and creating user-friendly software tools that can be deployed in a variety of environments.

Data science researchers and practitioners work side by side to apply advanced theories, methods, algorithms, models, evaluation tools and testbeds, and computational-based solutions to address complex scientific challenges affecting a wide range of domains and application areas. Core domain knowledge is beneficial, such as in the?nuclear, biological, energy, materials, or chemical science spaces.?

The successful candidate will work in interdisciplinary teams to develop and address challenging problems as well as contribute to software solutions, new project ideas, written reports and publications, and technical presentations. Strong written and verbal communication skills and ability to work with a diverse team are desired.

Responsibilities

Expectations of our early-Career Data Scientists include:

+ Contribute professionally to a diverse team

+ Build professional reputation for technical expertise

+ Explore, manage, and experiment with data to answer research problems

+ Applying and interpreting standard theories, principles, methods, and tools in statistics, such as experimental design, spatial statistics (e.g., kriging), and machine learning algorithms to national security applications

+ Excellent verbal and written communication skills and the ability to work in a collaborative environment through written reports and slide presentations that communicate statistical approaches and findings to non-technical audiences

+ Using high-level programming language programming, such as R and python

+ Building software tools for data visualization, data cleaning, and algorithm implementation, such as R Shiny

+ Image processing and image analysis

+ Ownership in professional goal setting and development

+ Passionate and self-motivated with good time management skills

Qualifications

Minimum Qualifications:

+ BS/BA or higher

Preferred Qualifications:

+ MS in statistics, mathematics, or related field

Hazardous Working Conditions/Environment

Not Applicable

Additional Information

Not Applicable

Testing Designated Position

This is not a Testing Designated Position (TDP).

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, flexible work schedules and telework options. 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 b