Spring '27 Intern - Perception/Robotics

Moss; San Francisco, Northern (CA, KY); Hybrid; USD 34,000 - 55,000; Part time

Job summary

Moss in San Francisco is seeking co-ops and/or part-time Perception or Robotics Interns to help build perception, mapping, ML, and autonomy systems for outdoor robots. You’ll work on sensor fusion, 3D mapping with LiDAR, cameras, and GPS, and deploy models on edge hardware.

You’ll own projects from research to deployment, collaborate with engineers across software, hardware, and mechanical teams, and gain hands-on experience with real robots in challenging environments.

Qualifications

• Robotics, perception, ML, CV and mapping project experience beyond coursework.
• Strong programming in C++, Python, or Rust.
• Experience with 3D sensor data, sensor fusion, localization or navigation.
• Comfortable with Linux and debugging real systems.
• Willingness to learn quickly and take ownership on real robots.

Responsibilities

• Own projects from research and design through prototyping, deployment, and iteration on real robots
• Build perception and mapping systems that turn multi-sensor data into useful, production-ready outputs
• Train and evaluate machine-learning models using outdoor datasets
• Develop sensor fusion across LiDAR, cameras, GPS, and environmental sensors
• Build and improve localization, navigation, controls, and robot behaviors
• Integrate perception, autonomy, and hardware into reliable end-to-end robotic systems
• Develop tools for data collection, labeling, training, evaluation, simulation, and field debugging
• Optimize models and algorithms for latency, memory usage, and reliability on edge hardware
• Test and deploy robotic systems during real-world customer operations
• Collaborate closely with perception, software, electrical, and mechanical engineers

Skills

Robotics

Perception

Machine learning

Computer vision

Mapping

C++

Python

Rust

Tools

Linux

CUDA

Edge deployment

Point clouds

Job description

About Us

At moss.ag, we build robots to go where humans won't, digitizing the physical outdoor world to make it machine-readable. Starting with tree farms — where a single field holds millions of plants no human has ever fully inventoried.

We’re a small team of practical engineers with a long-term vision. We focus on real, messy, on-the-ground problems today, while working toward a future where autonomous field robots make harsh outdoor jobs easier and safer.

If our mission aligns with how you work and think, we’d love to learn more about you!

The Role

Join us as a Perception or Robotics Intern on a fast-moving team of seven. In this high-ownership role, you’ll help build and ship the perception, mapping, machine learning, and autonomy systems that allow our robots to understand and operate in complex outdoor environments.

Depending on your interests and experience, you may work on sensor fusion and 3D mapping using LiDAR, cameras, and GPS; train perception models on custom datasets; develop localization, navigation, and robot behaviors; or integrate these systems into reliable robots deployed in the field.

You’ll help make our systems work through changing light, harsh shadows, motion, dust, vegetation, uneven terrain, and severe occlusions while optimizing them for real-time performance on edge hardware.

We’re looking for for co-ops and/or part-time roles.

Minimum Requirements

• Impressive technical projects beyond the classroom in robotics, perception, machine learning, computer vision, mapping, or related fields
• Strong programming skills in C++, Python, or Rust
• Hands-on experience with at least one of the following:
  • 3D sensor data, point clouds, or sensor fusion
  • Machine learning or computer vision
  • Localization, mapping, navigation, controls, or robot behaviors
• Comfortable working in Linux and debugging real systems
• Excited to learn quickly, take ownership, and test your work on real robots
• Experience with LiDAR, cameras, model training, CUDA, or edge deployment is valuable but not required.

What You'll Do

• Own projects from research and design through prototyping, deployment, and iteration on real robots
• Build perception and mapping systems that turn multi-sensor data into useful, production-ready outputs
• Train and evaluate machine-learning models using custom outdoor datasets
• Develop sensor fusion across LiDAR, cameras, GPS, and environmental sensors
• Build and improve localization, navigation, controls, and robot behaviors
• Integrate perception, autonomy, and hardware into reliable end-to-end robotic systems
• Develop tools for data collection, labeling, training, evaluation, simulation, and field debugging
• Optimize models and algorithms for latency, memory usage, and reliability on edge hardwareTest and deploy robotic systems during real-world customer operations
• Collaborate closely with perception, software, electrical, and mechanical engineers