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

Maven Robotics, Inc.; San Francisco (CA); On-site; USD 150,000 - 230,000; Full time

Job summary

Maven Robotics, Inc. in San Francisco seeks a skilled Machine Learning Engineer - Robot Manipulation to design, implement, test, and deploy manipulation algorithms for assembly and material handling.

You will work across RL and IL, translate goals into robust models, and ensure real‑world performance on robotic systems, while mentoring teammates in a fast‑paced startup. Experience with Gazebo/MuJoCo and edge deployment is a plus.

Qualifications

• MS or PhD in machine learning, computer science, robotics, or a related field.
• Strong practical experience training and deploying machine learning models for real-world applications.
• Deep understanding of reinforcement learning (RL) and imitation learning (IL) and their application to robotics.

Responsibilities

• Design and implement machine learning algorithms, with a focus on RL and IL, to enable robotic manipulators to perform complex tasks in dynamic environments.
• Translate high-level objectives into machine learning problems and deploy robust, scalable models to real-world robotic systems.
• Integrate ML solutions into existing robotics workflows, ensuring models perform well in simulated and real-world settings.
• Drive innovation by incorporating latest research in ML into practical applications for robotic manipulation.
• Take ownership of critical ML projects from conception to deployment.
• Collaborate across disciplines and mentor junior engineers.

Skills

Python

PyTorch

Reinforcement Learning

Imitation Learning

Data management

Self-starter

Startup environment

Education

MS in ML/CS/Robotics

PhD in related field

Tools

Gazebo

MuJoCo

Stable Baselines

RLlib

Job description

LOCATION:

Role Description

We are looking to recruit an exceptional Machine Learning Engineer - Robot Manipulation to design, implement, test, and deploy robot manipulation algorithms that enable assembly and material movement tasks.

In this role you will:

• Design and implement machine learning algorithms, with a focus on reinforcement learning (RL) and imitation learning (IL), to enable robotic manipulators to perform complex tasks in dynamic environments.
• Translate high-level objectives into machine learning problems and deploy robust, scalable models to real-world robotic systems.
• Integrate your ML solutions into existing robotics workflows, ensuring that models are performant in both simulated and real-world settings.
• Drive innovation by incorporating the latest research in machine learning into practical applications that push the boundaries of robotic manipulation.
• Take ownership of critical ML projects, seeing them through from conception to successful deployment.
• 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 practical experience in training and deploying machine learning models for real-world applications.
• Deep understanding of reinforcement learning (RL) and imitation learning (IL) and their application to robotics.
• Proficiency in programming languages and tools commonly used in machine learning (e.g., Python, PyTorch).
• 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:
• Designing and implementing reward functions for complex manipulation tasks.
• Developing models that can handle noisy, incomplete, or sparse data.
• Deployment of ML models to edge devices for real-time inference.
• Accelerating ML training processes using GPU, TPU, or other HW accelerators.
• Using reinforcement learning frameworks, e.g. Stable Baselines, RLlib, or similar.
• General knowledge of robotics principles, including kinematics, dynamics, and control.
• Publications or contributions to the machine learning community, particularly in areas related to robotics or reinforcement learning.