About the Company

Cartesian is building spatial intelligence for indoor environments to drive operational efficiency.

We’re tackling one of the biggest challenges in the $35T global retail industry: in-store inventory visibility. Our platform delivers accurate indoor positioning and actionable product location insights, helping retailers streamline operations, optimize workflows, and reduce inefficiencies. By fusing wireless signals and mobile computer vision, we provide a uniquely scalable and infrastructure-free solution already deployed by international fashion brands.

Founded by an MIT engineering professor and alum behind the award-winning, patented core technologies, Cartesian spun out in 2023. Originally backed by the prestigious SBIR Award from the US National Science Foundation, we've bootstrapped to a live product that's now deployed in over a dozen countries and have been aggressively scaling in the market.

About the Role

 

We’re now looking for a highly motivated, product-oriented Applied Research Scientist to join our core R&D team at a pivotal moment in our growth. You'll have a direct impact on core algorithms, take ownership of new features, and shape the technical roadmap of a category-defining product. We move fast, care deeply about quality, and value people who take initiative and crave real-world impact. You’ll be joining us in-person in the heart of Kendall Square, Cambridge, next to MIT and the Charles River.

 

Responsibilities

• Work on core algorithmic problems that blend modeling, estimation, and perception
• Build and run experiments and benchmarks on real data from live deployments
• Translate research prototypes into robust production pipelines (mobile, edge, cloud) in collaboration with engineering
• Work across engineering and product to define and deliver new features for enterprise customers
• Monitor, analyze, and improve system performance in real world conditions and scale
• Develop datasets, metrics, and tools that help us measure and improve performance
• Help shape new product capabilities and directions as we expand
• Own problems end to end from framing to deployment

 

Qualifications

• PhD in computer science or related field
• Deep understanding and practical experience in at least one of the following areas: machine learning, signal processing, transformer models, probabilistic models (e.g., state estimation), SLAM, MDP, GNNs, 3D reconstruction, sensor-fusion models, …
• Publications in top-tier ML, vision, or systems venues (e.g., ACL, NeurIPS, CVPR, ECCV, ICCV, MobiCom, MobiSys, MLSys, ICASSP).
• Ability to write high-quality, maintainable code.
• Excellent communication skills and ability to collaborate across disciplines.
• Curiosity, initiative, and a desire to work on problems that do not have clean answers while still able to focus on real-world impact
• Thrive in fast-paced, dynamic environments and take pride in producing high-quality work.

 

Nice to Have

• Past startup experience
• Industry experience in applied software or ML engineering.
• Familiarity with cloud-based model training and inference.
• Background in wireless localization, radar signal processing, or computer vision.

 

Pay range and compensation package

$125,000 - $175,000 annually