Robot Learning Research Engineer — Real-World Manipulation

Woven; Palo Alto (CA); On-site; USD 120,000 - 300,000; Full time

Benefits offered by this job

Early equity with meaningful upside

Ship ML models to live robots

Exposure to full robotics stack

Direct ownership of learning systems

Job summary

Mundane is a venture-backed seed-stage robot learning startup founded by a team of Stanford researchers and builders. We’re deploying a massive fleet of humanoid robots to perform mundane tasks in commercial environments, collecting data to build the next generation of embodied intelligence.

We’re a fast-paced, execution-driven team of engineers, roboticists, and dreamers. You’ll develop the learning systems that give our robots adaptability in the real world, from data pipelines to training and

Qualifications

• Strong proficiency in Python and experience with ML frameworks.
• Hands-on experience with robotic software stacks (ROS2, real-time control, perception pipelines).
• Background in reinforcement learning, imitation learning, or embodied AI.
• Experience deploying ML models to real-world systems, not just simulation.

Responsibilities

• Design and implement ML algorithms for robot perception, control, and decision-making.
• Build and maintain data pipelines for large-scale collection, labeling, and training from robots in the field.
• Develop real-time inference systems that integrate with the robotics stack.
• Collaborate with controls, perception, and embedded teams to deliver autonomous systems.
• Optimize models for reliability, latency, and performance on hardware-constrained platforms.
• Push forward new approaches in robot learning, including imitation learning and foundation models.

Skills

Python

Tools

PyTorch

TensorFlow

JAX

ROS2

Real-time control

Job description

Mundane is a venture-backed seed-stage robot learning startup founded by a team of Stanford researchers and builders. We’re deploying a massive fleet of humanoid robots to perform mundane tasks in commercial environments, collecting data to build the next generation of embodied intelligence.

We’re a fast-paced, execution-driven team of engineers, roboticists, and dreamers. You’ll develop the learning systems that give our robots adaptability in the real world, from data pipelines to training and