Machine Learning & Digital Signals Processing Engineer

Quartermaster

About The Position

At Quartermaster AI, the mission is to make the ocean a safe and sustainably managed resource by leveraging cutting-edge AI and robotics. The company's distributed open-ocean systems enable vessels to sense, compute, and communicate, enhancing maritime domain awareness. The role is for an Artificial Intelligence Engineer with an emphasis in RF analysis, tasked with developing and deploying machine learning systems that use SDR data for real-time maritime intelligence. The engineer will build AI models to provide contextual understanding of vessel activity based on observed RF signatures. This position is suited for someone who can tackle challenging, sometimes ambiguous problems, connect theory with implementation, and is enthusiastic about building AI systems that function in dynamic, constrained, and remote environments.

Requirements

7+ years of experience building and deploying machine learning systems, with a focus on multi-modal, graph theory, and sensor fusion applications.
Proficiency in Python and deep learning frameworks such as PyTorch and Torchsig.
Deep understanding of signal alignment, temporal/spatial synchronization, and feature extraction across diverse data types.
Proven ability to bridge research and application—delivering high-performance models in production contexts.
Excellent communication and collaboration skills in cross-functional, interdisciplinary teams
Must be eligible to obtain/maintain a security clearance.

Nice To Haves

PhD or Master’s degree in Machine Learning, Computer Vision, Signal Processing, or a closely related field.
Experience in maritime, aerospace, or other sensor-rich environments is a significant plus.
Experience with Nvidia Jetson modules.

Responsibilities

Research, design, and implement advanced machine learning models that combine vision, RF, and acoustic signals for detection, classification, and tracking tasks.
Architect sensor fusion pipelines that support robust, redundant, and context-aware perception in dynamic environments.
Collaborate closely with domain experts and systems engineers to translate raw sensor data into actionable model inputs.
Design and oversee data pipelines for multi-modal learning, including data alignment, augmentation, and pre-processing across modalities.
Optimize models and inference workflows for low-latency execution on embedded and edge compute platforms.
Lead performance analysis across individual and fused modalities, and drive strategies for improving robustness and generalization.
Prototype and operationalize novel research in sensor fusion, uncertainty modeling, and representation learning.
Contribute to long-term architectural decisions around multi-modal AI infrastructure, tooling, and evaluation frameworks.
Document model design, training methodology, and validation processes with rigor and clarity.