ResponsibilitiesPNNL is seeking a Data Scientist II to investigate and develop deep learning methods for undersea acoustics. You will analyze acoustic data, formulate and test algorithms, and develop, train, and evaluate deep learning models for detecting, classifying, localizing, or characterizing underwater sources and phenomena. This research supports national security missions and may address challenges relevant to naval sensing and undersea operations.
In the AI and Data Analytics Division, you will independently carry out defined research tasks as part of a team developing analytical methods and tools that support 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 for detecting, classifying, or characterizing underwater sources. The role also offers opportunities to explore related problems in time-series analysis, representation learning, anomaly detection, uncertainty quantification, and multimodal sensing. Candidates with deep learning experience in undersea acoustics, sonar, audio, radar, seismic, or related sensing applications are encouraged to apply. The role may also include prototyping and evaluating agentic SI systems that combine deep learning with acoustic analysis tools.
You will work alongside researchers and domain specialists on difficult national science and technology challenges. Collaboration with software and machine learning (ML) engineers will reflect each project's needs and stage of development, including transition of tested methods into usable tools. Opportunities to advance existing research and pursue new ideas may come through ongoing projects, internal research investments, or new proposals.
Key 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 SI systems with software and ML 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.
This position is based in either Richland, WA or Seattle, WA and requires an onsite presence.QualificationsMinimum Qualifications:
- BS/BA and 2 years of data science experience -OR-
- MS/MA -OR-
- PhD
- 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.
Preferred Qualifications:
- 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.
Hazardous Working Conditions/EnvironmentNot Applicable
Additional InformationThis 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.
