Lead Perception Engineer

Gravis Robotics is a startup that turns heavy construction machines into intelligent and autonomous robots. Our unique combination of learning-based automation and augmented remote control lets one operator safely conduct a fleet of earthmoving machines in a gamified environment. Our team has over a decade of academic experience honing the cutting edge of large-scale robotics, and is rapidly growing to bring that expertise into a trillion dollar industry through active deployments with market leaders.

About the Job

At Gravis, we engineer solutions at the nexus of hardware and software every day: bringing new perception and control technologies onto awesome, autonomous machines. Our Rooftop Autonomous Control Kit (Rack) combines sensors, compute, communication and networking modules toward a manufacturer-agnostic solution that can be applied to a variety of construction machines regardless of type and age.

We are seeking a highly skilled and experienced lead for our perception team: you will spearhead the perception development process, from design and prototyping to deployment of state-of-the-art object detection, scene segmentation, mapping, state estimation and calibration algorithms—while ensuring production quality implementation and timely execution.

Responsibilities

• Manage the design, prototyping, and deployment of advanced real-time perception and deep learning algorithms for autonomous heavy machines, focusing on 3D object detection & tracking, semantic segmentation, visual/lidar odometry, mapping, and sensor calibration.
• Lead the perception team and the agile development process, working with leadership to set and maintain project timelines.
• Establish and optimize testing procedures and performance metrics to ensure robust system behavior.
• Oversee the integration of new sensors and configurations into the perception stack.
• Collaborate closely with multidisciplinary experts to improve the reliability and performance of the entire system.
• Propose and manage hiring initiatives to strategically build a nimble and highly effective perception team.

Qualifications

• Master’s or PhD in Computer Science, Mechanical Engineering, Electrical Engineering or a related field.
• 5+ years of experience in developing and implementing robust perception algorithms.
• Writing production-quality C++/Python code in a Linux development environment.
• Extensive experience with deep learning frameworks (pytorch, tensorflow, etc) using image and/or LiDAR data.
• Proven leadership in a collaborative, small-team environment, with a strong ability to drive projects across disciplines.
• Excellent project management skills with the ability to prioritize tasks, manage resources, and meet deadlines.
• Excellent communication skills with the ability to effectively convey technical concepts to both technical and non-technical stakeholders.
• Experienced with setting up and maintaining machine learning pipelines, from data collection to model deployment
• Proficiency with common robotics & perception frameworks ( e.g. OpenCV, PCL, Open3D, ROS 2, Nvidia HW/SW ecosystem, etc.)