At Expedition Technology (EXP), we solve the nation’s toughest defense and intelligence challenges through advanced analytics, machine learning, and software engineering. Our teams work at the intersection of mission and innovation, delivering impactful capabilities in real-world environments.

We are seeking an Embedded Software Engineer to support the deployment of advanced data processing and machine learning solutions to low size, weight, and power (SWaP) systems. This role focuses on optimizing and deploying algorithms to GPU-enabled embedded platforms (e.g., NVIDIA Jetson) for real-time applications.

· Deploy and optimize computer vision, signal processing, or data processing algorithms on embedded hardware

· Improve real-time, low-latency performance of ML pipelines on constrained systems

· Profile CPU/GPU performance and identify system bottlenecks

· Collaborate on algorithm selection based on hardware constraints

· Containerize and deploy solutions using tools like Docker

· Work in Linux-based environments and contribute to production-quality code

· Partner with ML and software engineers to transition models into operational environments

· United States Citizenship – for US Government security clearance eligibility

· Active Top Secret/SCI (TS/SCI) security clearance

· Experience deploying software or algorithms to embedded or edge systems

· Proficiency in Python or ability to learn quickly

· Experience working in Linux environments

· Experience optimizing performance in constrained environments

· Strong problem-solving skills across software and hardware domains

· Experience with NVIDIA Jetson or similar GPU-enabled embedded platforms

· Experience with video or signal processing pipelines

· Familiarity with CUDA and CPU/GPU profiling

· Experience with Docker or containerization

· Experience with ML frameworks such as PyTorch or ONNX

· Prior experience working on ML-focused teams

This role is focused on embedded systems with GPU acceleration rather than traditional microcontroller or FPGA-centric work. Candidates should be comfortable working across the full lifecycle of algorithm development and deployment in performance-sensitive environments.