Perception Engineer

About Mach9

Mach9 is pioneering the next era of the surveying and geospatial industry. Our AI-driven platform opens up a world of possibilities for the millions of surveyors and civil engineers responsible for supporting the $3 trillion infrastructure industry. With our market-defining technology, engineers can leverage geospatial data to complete projects faster than ever before.

Our first product, Mach9 Digital Surveyor is transforming the highly-manual surveying workflows by automatically extracting features (such as signs, curbs, and utility poles, etc.) from large-scale imagery and 3D datasets—delivering results up to 96 times faster than today’s labor-intensive process. By dramatically scaling what surveyors can achieve, Mach9 empowers the industry to accelerate infrastructure development, improve decision-making, and fundamentally reshape the way we build and maintain our world.

Mach9 is backed by Quiet Capital, Y Combinator, Overmatch Ventures, Kyle Vogt (founder of Cruise), Amar Hanspal (former CEO of Autodesk), Scott Belsky (CPO of Adobe), Gokul Rajaram (former executive at DoorDash), and more.

What you’ll do:

• Develop and optimize advanced machine learning and computer vision algorithms.

• Apply your expertise to improve feature detection and localization in 2D imagery and 3D point cloud data.

• Innovate and experiment with novel model architectures, aiming to enhance our 3D geospatial model's accuracy and efficiency.

• Work collaboratively within a team of engineers and researchers, contributing to a culture of innovation and knowledge sharing.

• Mentor and guide junior team members, fostering an environment of growth and learning.

What we’re looking for:

• Strong background in computer vision and machine learning, with a preference for practical orientation over purely academic accomplishments.

• Significant experience in the field, with a track record of leading projects and mentoring junior engineers.

• Proficiency in programming languages relevant to ML and CV, particularly Python and C++ (or equivalent languages), with the ability to write efficient, maintainable code.

• Experience building and training 2D or 3D computer vision deep neural networks.

• Experience with 3D reconstruction and other relevant CV technologies, with a preference for candidates familiar with a mix of classical and learned approaches.

• Ability to independently manage and track progress on projects, demonstrating a high degree of self-motivation and accountability.

• Ideally a Masters or PhD in ML, Computer Vision, or Robotics.

• 3+ years of experience in computer vision or machine learning.