ROLE Machine Learning Engineer - Robot Perception Design, implement, test and deploy robot perception algorithms for industrial applications

Maven Robotics; San Francisco, Northern (CA, KY); Hybrid; USD 150,000 - 190,000; Full time

Job summary

Maven Robotics is seeking a Machine Learning Engineer - Robot Perception to design and deploy perception algorithms powering our autonomous robots. You will work on object detection, pose estimation, tracking, and scene understanding integrated with sensor fusion.

You will collaborate with hardware teams to calibrate sensors, optimize models for edge deployment, and advance our AI and autonomy stack in a fast-paced startup setting.

Qualifications

• Must have MS or PhD in machine learning, computer science, robotics, or related field.
• Proficient in computer vision, deep learning, and sensor fusion.
• Strong experience with Python and C++, and frameworks like PyTorch, TensorFlow, OpenCV, and ROS.
• Hands-on experience with robotics perception systems (SLAM, 3D reconstruction, multimodal perception).
• Experience with hardware calibration of cameras, LiDAR, and sensors.
• Ability to thrive in a fast-paced startup environment and mentor junior engineers.

Responsibilities

• Design, implement, test, and deploy robot perception algorithms for object detection and scene understanding.
• Develop and integrate sensor fusion from cameras, depth sensors, IMUs and tactile feedback.
• Optimize real-time perception pipelines for low latency in dynamic environments.
• Collaborate with hardware engineers to optimize sensor configurations for onboard deployment.
• Contribute to the broader AI and autonomy stack and ensure smooth integration with planning and control.
• Provide technical mentorship and knowledge sharing across the team.

Skills

Computer vision

Deep learning

Sensor fusion

Python

C++

Self-starter

Education

MS or PhD in ML, CS, robotics

Tools

PyTorch

TensorFlow

OpenCV

ROS

NVIDIA Jetson

Job description

LOCATION:

Role Description

We are looking to recruit an exceptional Machine Learning Engineer - Robot Perception to design, implement, test, and deploy robot perception algorithms that power our robots’ ability to understand and interact with the world.

In this role you will:

• Develop, train, and deploy ML-based perception algorithms for object detection, pose estimation, tracking, and scene understanding.
• Integrate sensor fusion techniques using cameras, depth sensors, IMUs, and tactile feedback.
• Optimize real-time perception pipelines for low-latency and robust performance in dynamic environments.
• Work closely with hardware engineers to design sensor configurations and optimize perception models for onboard deployment.
• Contribute to our broader AI and autonomy stack, ensuring seamless integration with reasoning, manipulation, planning and control.
• Collaborate across disciplines to ensure seamless integration of ML models and provide technical mentorship to junior engineers.

Qualifications

Must-have:

• MS or PhD in machine learning, computer science, robotics, or a related field.
• Strong background in computer vision, deep learning, and sensor fusion.
• Proficiency in Python and C++, with experience in frameworks like PyTorch, TensorFlow, OpenCV, and ROS.
• Hands-on experience with real-world robotics perception systems (e.g., SLAM, 3D reconstruction, multimodal perception).
• Experience working with hardware, including setting up and calibrating cameras, LiDAR, and other sensors.
• Experience with data collection, preprocessing, and management in the context of training ML models.
• Self-starter attitude with strong ability to identify problems, prioritize them, then plan and execute working solutions.
• Enthusiasm for working in a fast paced startup environment and eagerness to support the team on a variety of topics.

Nice-to-have:

• Familiarity with robotic simulation environments (e.g., Gazebo, MuJoCo) and experience in sim-to-real transfer.
• Experience in:
  • Developing models that can handle noisy, incomplete, or sparse data.
  • Deployment of ML models to edge devices for real-time inference (e.g., NVIDIA Jetson).
  • Accelerating ML training processes using GPU, TPU, or other HW accelerators.
  • General knowledge of robotics principles, including kinematics, dynamics, and control.