Robotics Perception Engineer

Are you an elite engineer looking for the freedom and resources to achieve the impossible? THEN COME BUILD GIANT TERRAFORMING ROBOTS THAT WILL BUILD A BETTER FUTURE!

At TerraFirma, we're not just building robots —we’re redefining how the world moves earth for construction.

Our team, founded by former SpaceX engineers and backed by Bain Capital Ventures, is driven by a mission to make construction faster, more efficient, and more sustainable through pragmatic human-in-the-loop automation.

Our Mission:

TerraFirma was founded to build a brighter future for humanity by revolutionizing how we construct the large-scale physical infrastructure our civilization desperately needs. From enabling mega-scale renewable energy projects and constructing resilient cities, to building efficient transportation and eco-friendly water infrastructure, our work today paves the way for a brighter, more sustainable future. The first step in all of these projects is to move massive amounts of dirt incredibly efficiently. As we look to the stars, we recognize that mining, processing, and moving raw materials will be the foundation of humanity's expansion into the cosmos. TerraFirma is pioneering the technology that will not only secure a sustainable future for humanity on Earth but also unlock the boundless possibilities of interplanetary expansion.

Our Company:

TerraFirma was founded by two engineers named Noah who met while studying engineering at Princeton. After Princeton, both contributed to cutting-edge projects at SpaceX, where Noah Schochet (CEO) designed and mass-produced the Starlink user terminals and Starship rockets, and Noah McGuinness (CTO) developed flight software for SpaceX's satellite constellation. Now, they're taking the SpaceX Mentality -- rapid iteration based on engineering first principles -- to the construction industry. Their experience in pushing the boundaries of space exploration now fuels TerraFirma's mission to transform how we build the world's critical infrastructure here on Earth.

We are moving at light speed, and are ready to start scaling. Our fully functional ecosystem retrofits existing earthmoving machines (excavators, bulldozers, loaders, etc.) and enables one operator to control three or more machines simultaneously. Our headquarters, AKA Robot Ranch, is located in Austin, TX. We are committed to iterating and improving as rapidly as possible. To that end, we have fully stocked mechanical and electrical workshops, giant machines to retrofit, plenty of land to test on, and we are surrounded by earthworks projects with customers eager to start using our technology.

What we're looking for:
We’re seeking innovators, boundary-pushers, and people who will move heaven and earth to achieve the impossible. If you are someone who:

• Is driven by a relentless need to make the world better

• Thrives in fast-paced, high-pressure environments

• Hates being a cog in a machine and wants extreme ownership and opportunities to learn

• Has developed versatile technical skills by building amazing projects

• Can wear many hats, and loves learning new skills quickly

Then you're in the right place!

The Role:

In this role, you won’t just be an employee - you’ll be a trailblazer. You should expect to take hands-on ownership over a variety of projects related to robotic perception and autonomous control systems. You will own high-level decisions for software and sensor architecture, as well as direct implementation and testing of algorithms on physical hardware. Day-to-day responsibilities will involve rapidly prototyping and testing sensor systems as well as data processing algorithms and pipelines to extract required data from multi-dimensional, high-bandwidth input sources such as images or point clouds. You will coordinate with other software and electrical engineers to design new systems and implement, optimize, and accelerate software written in C, C++, and Python to run with real-time constraints. Engineers in this position should additionally expect to solve problems related to sensor calibration, pose estimation, localization, online and offline model training, and new sensor integration. This role is best suited for fast learners who are comfortable working with a high degree of autonomy and a large scope of responsibility.

Responsibilities:

• Integrate multi-spectral and TOF sensors into robotic systems with real-time processing constraints

• Work with motion and trajectory planning teams to design and synthesize sensor systems to extract required signals and inputs

• Implement algorithms to efficiently detect objects of interest from incoming data streams for the purposes of collision avoidance, motion planning, and trajectory planning

• Stitch together and manipulate camera feeds and data from other sensors to effectively visualize the state of physical systems to human operators

• Develop real-time pipelines for processing, sharing, and fusing data from multiple sensor sources

• Train Machine Learning (ML) models on existing and custom datasets and support collection and labeling of data for additional training and validation

• Develop simulation and visualization tools to aid in rapid prototyping of robotic software and control algorithms

• Own the integration, calibration, and testing of sensors, both for proof-of-concept prototypes and production systems

• Lead interdisciplinary teams, mentor new employees, and actively participate in the hiring process
  

Basic Qualifications:

• Bachelor of Science in robotics, mechanical engineering, physics, computer science, electrical engineering, or a closely related field

• 3+ years of professional or project experience with robotic software development, involving implementation of real-time algorithms for perception and data processing pipelines

• Demonstrated experience owning large-scale deliverables, leading teams, and driving product roadmaps

Preferred Skills & Experience:

• Experience working with safety-critical or real-time systems

• Experience working with embedded applications for robotics, autonomous vehicles, aerospace, automotive, or construction

• Proficiency in C++ and Python, including development for Linux-based systems and bare-metal MCUs

• Experience training, testing, optimizing, and deploying online and offline machine learning models with existing and custom datasets

• Experience implementing algorithms or pipelines for robotic systems or feedback control from scratch in C++ or Python

• Experience performing object detection on multiple data sources including multi-spectral images and point clouds

• Experience programming FPGAs for high-throughput networking, compression, or DSP

• Ability to work autonomously in a fast-paced environment

Additional Requirements:

• Must be willing to work extended hours or weekends when needed to support critical deadlines or triage urgent deployment issues

• Must be willing to relocate to Austin, TX if not within commuting distance

Compensation & Benefits:

TerraFirma is committed to fair and equitable compensation practices. The annual salary range for this role is $100,000 - $170,000. Base compensation will vary based on factors such as relevant experience and education. Salaries and leveling will be determined on a case-by-case basis if an offer is extended. Our total compensation package also includes generous equity in TerraFirma. Relocation packages are available to compensate employees for moving costs if applicable.