Machine Learning Scientist

Cartesian Systems • Cambridge, MA

2d • Onsite

About The Position

Cartesian is seeking a highly motivated, product-oriented Machine Learning Scientist to join its core R&D team. The role will contribute directly to indoor positioning algorithms and models, take ownership of new features, and help shape the technical roadmap of the company’s spatial intelligence product. The scientist will design, develop, and deploy machine learning models for indoor positioning and perception, optimize model architectures for performance and efficiency, and create tools and datasets for real-world, large-scale benchmarking. The position also translates research into production pipelines and collaborates with engineering and product teams to deliver features to enterprise customers.

The role is based in person in Kendall Square, Cambridge, near MIT and the Charles River. Cartesian builds indoor spatial intelligence technology that combines wireless signals and mobile computer vision to improve retailers’ inventory visibility and operations.

Requirements

• PhD in computer science, electrical engineering, or a related field.
• Deep understanding of and hands-on experience with machine learning models for time-series data, including transformer-based architectures and probabilistic models such as state estimation.
• Publications in top-tier machine learning, vision, or systems venues, such as ACL, NeurIPS, CVPR, ECCV, ICCV, MobiCom, MobiSys, MLSys, ICASSP, ICML, ICRL, ICRA, or IROS.
• Ability to write high-quality production code.
• Excellent communication skills and ability to collaborate across disciplines.
• Ability to thrive in a fast-paced, dynamic environment and take pride in producing high-quality work.

Nice To Haves

• Past startup experience.
• Industry experience in applied software or machine learning engineering.
• Familiarity with cloud-based model training and inference.
• Experience optimizing and deploying machine learning models in mobile environments.
• Background in wireless localization or radar signal processing.
• Experience with computer vision or multi-sensor fusion techniques, such as 2D/3D perception, pose estimation, tracking, or SLAM.

Responsibilities

• Design, develop, and deploy machine learning models for indoor positioning and perception.
• Optimize model architectures for performance and efficiency.
• Develop tools and datasets to benchmark performance in real-world conditions and at scale.
• Translate research into production pipelines.
• Collaborate with engineering and product teams to ship features to enterprise customers.

What This Job Offers

• Job Type: Full-time
• Education Level: Ph.D. or professional degree