3D Reconstruction Scientist

About the role

Array Labs is building a new way to understand the physical world.

Today, most geospatial systems are built around flat imagery, incomplete elevation models, slow refresh cycles, or narrow-area surveys. The world increasingly needs something better: accurate, frequently updated 3D information about the places, infrastructure, terrain, and activity that shape human decisions.

Array is building that system. We are developing a coordinated fleet of radar satellites designed to create high-resolution 3D data products of the Earth at unprecedented scale, speed, and reliability. Our technology is built to work across wide areas, through clouds, day and night, and to support both commercial and government customers operating in environments where timely physical-world understanding matters.

We design and build our satellites, radar payloads, sensing systems, and data products end-to-end. Our goal is to make 3D geospatial intelligence dramatically more accessible, useful, and operationally relevant for customers in mapping, infrastructure, disaster response, defense, intelligence, energy, telecommunications, mining, and other industries that depend on understanding the changing Earth.

About the Job

As a 3D Reconstruction Scientist on this team, you will develop and deploy algorithms that reconstruct 3D structure from distributed radar and optical sensors. You’ll work on multi-view geometry, tomography, and large-scale inverse problems, and you’ll be responsible for taking methods from prototype to production on real satellite data. The approaches you design will directly set the limits on the resolution, accuracy, and reliability of Array’s 3D products.

As part of our quickly growing engineering team, you will play a critical role in the design of the world’s most advanced radar satellite constellation—one that will significantly improve humanity’s ability to rapidly and comprehensively understand our changing planet.

Responsibilities - Research, design, and implement tomographic algorithms for 3D image reconstruction utilizing complex phase-history data from radar and optical sensors

- Develop autofocus techniques to sharpen images affected by inaccurate position knowledge of the sensor platform, and/or phase inaccuracies caused by various hardware imperfections in our distributed sensor system

- Develop efficient data preprocessing and calibration techniques to enhance the quality and accuracy of 3D reconstructions

- Optimize algorithms for near real-time production of 3D imagery in our cloud-based production pipeline

- Collaborate with cross-functional teams to integrate 3D image reconstruction solutions into our products and services

- Conduct thorough testing, validation, and performance evaluation of 3D image reconstruction algorithms to ensure they meet end-user expectations

Basic Qualifications - Bachelor's in Computer Science, Electrical Engineering, or a related field

- 4+ years of experience in 3D image reconstruction, 3D computer vision, multi-view geometry or a related field