Machine Learning Engineer (Intelligence & Sensing)

Job Description:

The engineer in this role will join a small, multidisciplinary R&D team focused on developing and advancing high-performance computer vision and perception models for intelligence, defense, and biomedical applications. The engineer will design and implement predictive and generative machine learning models for object detection, recognition, and tracking with an emphasis on robustness, accuracy, and scalability across diverse operational conditions. This role involves close collaboration with researchers and engineers to translate domain-specific challenges into effective learning-based solutions and to deploy production-quality models across desktop, cloud, and edge software environments.

The successful candidate will contribute across the full model development lifecycle, from problem definition and data exploration through training, evaluation, and deployment of robust, high-performance vision and tracking pipelines. Responsibilities include exploratory data analysis, neural network architecture design and tuning, integration with sensor data streams, and rigorous quantitative and qualitative evaluation to ensure accuracy, stability, and generalization. Emphasis is placed on developing reliable, scalable models and using GPU acceleration where appropriate. The engineer will collaborate closely with engineers and subject matter experts across multiple domains to deliver validated, production-ready solutions.

Basic Qualifications:

• Candidate must be a U.S. Citizen and possess (or be eligible to obtain) and maintain a SECRET clearance.
• Master’s degree in Computer Science, Electrical/Computer Engineering, Applied Mathematics, Physics, or a related STEM discipline.
• Strong proficiency in Python, with demonstrated experience developing and optimizing computer vision algorithms for real-time execution on embedded and edge platforms.
• Advanced understanding of computer vision and machine learning methods for object detection, object tracking, and object recognition,
• Proficiency with deep learning frameworks such as PyTorch or TensorFlow/Keras, including experience modifying or extending framework components to support custom vision pipelines and specialized hardware accelerators.

Desired Qualifications:

• Experience with embedded vision systems, including low-level optimization in C/C++ or assembly, and integration of perception algorithms with sensor data streams (e.g., EO/IR, video, or multimodal inputs).
• Proven track record of deploying computer vision and target tracking models into production environments, particularly on resource-constrained devices or distributed edge-compute architectures.
• Deep expertise in CUDA and/or OpenCL for accelerating image processing, neural network inference, and tracking pipelines on GPU-enabled systems.
• Experience with OpenGL and/or WebGL for real-time visualization of detections, tracks, sensor data, and algorithm outputs.
• Fluency working in Linux-based HPC and shared compute environments, with experience scaling training and evaluation of vision and tracking models across multiple GPUs or nodes.
• Experience collaborating within multidisciplinary engineering teams using Git-based version control workflows for code development, review, and integration.