Hybrid Machine Perception Engineer – Vision

at Quartermaster

• Job title: Machine Perception Engineer – Vision
• Job type: Full Time
• Experience level: Senior, Lead
• Salary: Not specified
• Degree requirement: Bachelor's Degree
• Tech skills: Python, PyTorch, Tensorflow
• Location requirements: Hybrid, California, United States

About the role

• Machine Perception Engineer focusing on vision systems deployment for maritime environments. Leading design and training of perception models for autonomous vessels.

Responsibilities

• Lead the design, training, and deployment of computer vision and perception models for tasks such as vessel detection, classification, and tracking.
• Architect and optimize inference pipelines for real-time performance on edge devices, including GPU-accelerated and mixed-precision inference.
• Implement and refine algorithms for scene understanding, object segmentation, and environmental awareness using both image and sensor fusion data.
• Collaborate with hardware and software teams to ensure model compatibility with embedded systems and available compute resources.
• Develop techniques for edge-case detection, dataset curation, and self-healing model behavior in dynamic, non-ideal environments.
• Apply active learning, domain adaptation, and synthetic data strategies to improve model robustness and generalization.
• Work closely with RF and sensor teams to integrate complementary signal data into multimodal classification and detection pipelines.
• Own model evaluation processes and benchmarking across hardware platforms and field conditions.
• Maintain best practices for model versioning, traceability, and validation in safety-critical applications.

Requirements

• Bachelors, Master’s or PhD in Computer Vision, Machine Learning, Robotics, or related field.
• 8+ years of experience in applied perception or computer vision, in performance critical applications
• Proficiency in Python and deep learning frameworks such as PyTorch or TensorFlow.
• Experience with model optimization techniques such as pruning, quantization, or TensorRT deployment.
• Strong understanding of classical vision (OpenCV) as well as modern deep learning methods.
• Familiarity with maritime, aerospace, or other harsh-environment sensing applications is a strong plus.
• Experience with sensor fusion, Kalman filtering, or multi-modal neural networks.
• Excellent problem-solving, debugging, and software design skills.
• Strong communication skills, with the ability to lead technical direction and mentor junior engineers.

Benefits

• Flexible working hours with occasional deadlines requiring high availability.
• Opportunity to work on innovative projects with a global impact.