Want to know if this job is worth applying to?
Virginia, United States
Hybrid
Not Available
Quartermaster is building the world's most comprehensive maritime intelligence platform. Our SmartMast™ system transforms commercial and civilian vessels into a persistent, distributed sensing network—combining HD video, AI, radar, RF sensing, and AIS to deliver real-time maritime domain awareness at global scale. With 600+ sensors deployed across 25+ countries and more than 400,000 vessels identified outside of AIS, we are setting a new standard for what ocean surveillance and safety can look like. We are a mission-driven, high-velocity team building dual-use technology for defense agencies, coast guards, and commercial maritime operators.
We are seeking a versatile and pragmatic Applied ML Engineer to contribute across a broad range of machine learning and perception tasks that power our edge-intelligent maritime systems. This role requires someone comfortable wearing many hats—from working with computer vision and sensor fusion models to building lightweight inference pipelines, designing experiments, and fine-tuning model behavior in production. You’ll work closely with a cross-functional team spanning hardware, software, and product to deliver real-world AI solutions that are robust, efficient, and reliable under challenging field conditions. This is an ideal position for someone who thrives on variety, rapidly shifting problem domains, and turning rough ideas into deployed systems.
Design, train, and evaluate models for tasks ranging from object detection and classification to anomaly detection and sensor-based inference.
Optimize model architectures and inference pipelines for performance on embedded/edge hardware under compute and bandwidth constraints.
Contribute to dataset development and labeling strategy, including data augmentation, synthetic data generation, and domain adaptation.
Support prototyping and experimentation across a variety of AI subfields, including computer vision, signal processing, and multi-modal fusion.
Implement real-time pipelines for processing sensor data on-device and in cloud environments.
Develop tools and scripts for benchmarking, data visualization, and debugging ML model performance.
Stay current with the latest research and tools in machine learning and evaluate their applicability to our product roadmap.
Participate in code reviews, team knowledge sharing, and internal technical documentation.
Must be eligible to obtain/maintain a security clearance.
Master’s or PhD in Computer Vision, Machine Learning, Robotics, or related field. Bachelors candidates considered on a case by case basis.
4+ years of experience building and deploying machine learning models in production environments.
Proficiency in Python and experience with deep learning frameworks such as PyTorch or TensorFlow.
Comfortable working with a range of data types (images, time-series, geospatial, RF, etc.).
Experience with edge or embedded ML deployments, including model compression and hardware-aware optimization.
Familiarity with common ML practices including cross-validation, hyperparameter tuning, and model monitoring.
Excellent debugging, experimentation, and problem-solving skills.
Strong collaboration and communication skills with both technical and non-technical team members.
Bonus: experience in maritime, aerospace, or other remote sensing domains.
Flexible working hours with occasional deadlines requiring high availability.
Opportunity to work on innovative projects with a global impact.
