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.

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.

Machine Perception Engineer – Vision

Key skills