Senior Robotics Manipulation Engineer: AI-Driven Control

Blackhornvc; Redwood City (CA); On-site; USD 170,000 - 225,000; Full time

Job summary

Dexterity seeks a Senior Robotics Manipulation Engineer to advance manipulation, control, simulation and learning using data-driven robot controls. You will stay current with reinforcement learning, motion planning and controls to strengthen Dexterity’s physical AI foundations.

You’ll work with sensor data, fusion and state estimation to inform planning and execution, collaborating with data, simulation, and robot operations teams to collect training data and build robust software.

Qualifications

• BS/MS/PhD in Computer Science or related discipline.
• 5+ years of relevant industry or research experience.
• Strong Python programming skills and proficiency in C++ on Linux.
• Experience with AI (imitation learning, RL, DL, LLMs) and distributed ML tooling.

Responsibilities

• Train models for robotic manipulation, force control, servoing, etc.
• Convert heuristics-based control to learned models.
• Develop the right state-space representation for our robotics systems.
• Collaborate with roboticists, ML engineers, mechanical engineers, and product managers to find optimal system solutions.
• Implement, test, and maintain high quality software.
• Lead efforts to improve the rigor and performance of models within Dexterity.

Skills

Python

C++

Linux

Reinforcement Learning

Imitation Learning

Deep Learning

LLMs

Distributed ML

Task & Motion Planning

Simulation

Startup experience

Education

BS/MS/PhD in Computer Science or related discipline

Tools

Git

Docker

Kubernetes

CI pipelines

Job description

Dexterity seeks a Senior Robotics Manipulation Engineer to advance manipulation, control, simulation and learning using data-driven robot controls. You will stay current with reinforcement learning, motion planning and controls to strengthen Dexterity’s physical AI foundations.

You’ll work with sensor data, fusion and state estimation to inform planning and execution, collaborating with data, simulation, and robot operations teams to collect training data and build robust software.