2026 Graduate - Synthetic Aperture Radar ML Engineer - Imaging Systems

Johns Hopkins Applied Physics Laboratory•Laurel, MD

About The Position

We are seeking an entry-level engineer or scientist to support the growth of RF/machine learning capabilities. The selected candidate will contribute in two primary areas: optimization of SAR-related processing for GPU-enabled edge hardware, and support of machine learning workflows including curated dataset development, model training, evaluation, and deployment to edge devices. This role is intended for a candidate with strong technical fundamentals and the potential to grow into a broader RF/ML contributor through mentorship and hands-on experience. Deep SAR expertise is not required.

Requirements

Bachelor’s or Master's degree in Electrical Engineering, Computer Engineering, Computer Science, Applied Mathematics, Physics, or relevant field.
Foundation in signal processing, linear algebra, and related applied mathematical methods.
Programming experience in Python, C++, or similar languages for technical computing, data processing, or algorithm development.
Familiarity with basic machine learning workflows, including data preparation, model training, evaluation, and performance assessment.
Ability to work with raw and processed data to create organized, curated datasets for analysis and model development.
Interest in performance optimization of computational pipelines, including familiarity with GPU or parallel computing concepts.
Awareness of edge or embedded computing constraints such as memory, latency, throughput, and power limitations.
Strong analytical, problem-solving, and communication skills.
Willingness to learn RF, SAR, and edge-deployed ML methods through mentorship and hands-on work.
Able to obtain an Interim Secret Clearance by your start date and can ultimately obtain a TS/SCI. If selected, you will be subject to a government security clearance investigation and must meet the requirements for access to classified information; eligibility requirements include U.S. citizenship.

Nice To Haves

Experience with GPU programming, accelerated computing, or performance optimization tools and frameworks.
Exposure to deploying software or machine learning models on embedded or edge computing platforms.
Familiarity with machine learning frameworks such as PyTorch, TensorFlow, or similar toolkits.
Exposure to RF systems, remote sensing, image formation, SAR, or related sensing modalities.
Experience with data curation, labeling, preprocessing, or dataset management for machine learning applications.
Experience working in Linux-based development environments.

Responsibilities

Support development and optimization of SAR-related algorithms and processing workflows for execution on GPU-enabled edge hardware.
Assist with profiling, debugging, and improving computational performance to meet edge-device constraints such as latency, memory, throughput, and power.
Build, organize, and maintain curated datasets for machine learning training, validation, and testing.
Develop and apply data preprocessing, labeling, and quality-check workflows to prepare data for analysis and model development.
Train, evaluate, and help refine machine learning models for deployment in edge or resource-constrained environments.
Support integration and deployment of algorithms and trained models onto edge computing platforms.
Collaborate with senior staff to transition prototypes into robust, testable implementations.
Document technical approaches, results, implementation details, and performance tradeoffs.
Work closely with mentors and team members to grow technical depth in RF, SAR, machine learning, and edge deployment applications.
Contribute to the team’s emerging RF/ML capabilities through applied development, experimentation, and technical learning.