Data Scientist II - Machine Learning for Undersea Acoustics

Pacific Northwest National Laboratory•Richland, WA

1d•Onsite

About The Position

Pacific Northwest National Laboratory (PNNL) is seeking a Data Scientist II to investigate and develop deep learning methods for undersea acoustics. The role involves analyzing acoustic data; formulating and testing algorithms; and developing, training, and evaluating models to detect, classify, localize, separate, or characterize underwater sources and phenomena. This research supports national security missions and may address challenges relevant to naval sensing and undersea operations. Within the AI and Data Analytics Division of the National Security Directorate, the employee will independently carry out defined research tasks as part of a team developing analytical methods and tools for acoustic analysis and national missions. Current priorities include applying deep learning to acoustic data and using Fourier analysis or signal processing to develop and evaluate methods. Related research may cover time-series analysis, representation learning, anomaly detection, uncertainty quantification, multimodal sensing, and prototyping and evaluating agentic AI systems that combine deep learning with acoustic analysis tools. The employee will work with researchers and domain specialists on national science and technology challenges, collaborating with software and machine learning engineers as appropriate to project needs and development stage. The work may include transitioning tested methods into usable tools, advancing existing research, and pursuing new ideas through ongoing projects, internal research investments, or proposals. The position is based in Richland, Washington, or Seattle, Washington, and requires onsite presence. The position requires the ability to obtain and maintain a federal security clearance. Applicants must be U.S. citizens and meet eligibility requirements for access to classified matter. The role is a Testing Designated Position requiring pre-employment and random drug testing, including compliance with stated federal requirements concerning illegal drug use. New employees must also obtain and maintain the applicable HSPD-12 Personal Identity Verification credential or, for eligible foreign national candidates, a favorable Local Site Specific Only federal risk determination until eligible for a PIV credential.

Requirements

Bachelor's degree and 2 years of data science experience, or a master's degree, or a Ph.D.
Experience developing, training, and evaluating deep learning models for acoustic, sonar, audio, radar, seismic, or related sensor data.
Experience implementing, training, and evaluating deep learning models in Python with PyTorch.
U.S. citizenship.
Ability to obtain and maintain a federal security clearance and meet eligibility requirements for access to classified matter.
Ability to satisfy applicable background investigation and drug-testing requirements, including demonstrating non-use of illegal drugs for the required period.

Nice To Haves

Experience developing and evaluating deep learning methods for undersea acoustic detection, classification, localization, or related problems.
Experience applying Fourier analysis or other signal processing methods to acoustic or related sensor data.
Experience with time-frequency representations or array-processing methods for acoustic analysis.
Familiarity with agentic AI systems and methods for evaluating their performance and reliability.
Familiarity with national security applications of deep learning and undersea acoustics.

Responsibilities

Develop, train, and evaluate deep learning methods for undersea acoustic detection, classification, localization, separation, and related problems.
Formulate and investigate research questions through Fourier analysis, signal processing, mathematical analysis, algorithm development, and experiments.
Design reproducible experiments and compare methods, examining detection and classification performance, false alarms, robustness to propagation and environmental variability, uncertainty, and computational demands.
Analyze and interpret results, document methods and limitations, and communicate findings to project leads, collaborators, and mission partners.
Prepare research code and evaluate agentic AI systems with software and machine learning engineers to transition tested methods into usable tools as appropriate.
Share technical knowledge across the team and mentor junior colleagues or students as appropriate.
Follow applicable quality, safety, and security requirements.