Senior Research Scientist - Network Systems

Peraton•,

1d•$146,000 - $234,000

About The Position

Peraton Labs is seeking a Senior Research Scientist to contribute to research and development addressing complex challenges for government agencies, utilities, and commercial customers. The organization’s work includes cybersecurity and network research to protect mission-critical systems and national cyber infrastructure, as well as technologies to efficiently use spectrum and system resources. The role focuses on RF communications and signal processing, machine learning and data applications, and their use in research spanning networking, wireless systems, cyber security, resilient networking, software-defined networking, and artificial intelligence. The successful candidate will have a record of work or publications spanning both RF/signal processing and machine learning, and will be able to take prototypes from concept through demonstration and communicate technical findings to stakeholders.

Requirements

Bachelor’s degree in Electrical Engineering, Computer Engineering, Computer Science, Applied Mathematics, or a related discipline, with at least 12 years of experience; alternatively, at least 10 years with an MS/MA or at least 7 years with a Ph.D.
Strong foundation in RF communications theory, including modulation/demodulation, propagation, link budgets, and spectrum analysis.
Hands-on experience with digital signal processing, including filtering, FFT/spectral analysis, detection, estimation, and adaptive algorithms.
Demonstrated expertise in compressive sensing, including sparse signal recovery, L1/L2 optimization, sensing matrix design, and sub-Nyquist sampling techniques.
Proficiency designing and implementing supervised, unsupervised, deep-learning, and reinforcement-learning algorithms, particularly for signal/time-series data.
Experience building end-to-end machine-learning pipelines from data ingestion through deployment and monitoring.
Knowledge of CNNs, RNNs/LSTMs, transformers, autoencoders, and GANs, with applied experience selecting models for RF/signal and data-analytic problems.
Strong data analytics skills, including exploratory analysis, statistical modeling, visualization, and deriving actionable insights from large or complex datasets.
Hands-on experience with PyTorch, TensorFlow/Keras, scikit-learn, and data tools such as NumPy, pandas, and Spark.
Experience with MLOps practices, including version control, Docker, CI/CD, experiment tracking (such as MLflow or W&B), and model serving.
Strong programming skills in Python and C/C++; MATLAB is a plus.
Experience with Git, Linux development environments, and scripting.
A project or publication record spanning both RF/signal processing and machine-learning domains.
U.S. citizenship.
Clear technical communication skills, including the ability to translate algorithms into implementation and results for stakeholders and to write technical papers and reports.
Self-directed approach and experience taking prototypes from concept through demonstration.

Nice To Haves

Experience applying machine learning to RF problems such as signal classification, spectrum sensing, RFI mitigation, cognitive radio, direction finding, or emitter identification.
Background in DoD or IC programs, electronic warfare, SIGINT, or radar systems.
Active security clearance, or ability to obtain one.

Responsibilities

Conduct research in RF communications and signal processing, including work involving modulation and demodulation, propagation, link budgets, and spectrum analysis.
Design and implement digital signal processing methods, including filtering, spectral analysis, detection, estimation, and adaptive algorithms.
Develop and apply compressive sensing techniques, including sparse signal recovery, optimization, sensing matrix design, and sub-Nyquist sampling.
Design and implement machine-learning algorithms for signal and time-series data, including supervised, unsupervised, deep-learning, and reinforcement-learning approaches.
Build end-to-end machine-learning pipelines covering data ingestion, preprocessing, feature engineering, training, validation, deployment, and monitoring.
Analyze complex datasets using exploratory analysis, statistical modeling, visualization, and other data analytics techniques.
Take prototypes from concept through demonstration and communicate algorithms, implementation, and results to stakeholders.
Write technical papers and reports.