Drimva

Apptronik

Staff Software Engineer - Humanoid Controls

$300K–$350K

Sunnyvale, CA +2 · Staff · Full-time · Posted Aug 12, 2026

Location
Sunnyvale, CA
Austin, TX
Sunnyvale, California, United States
Experience
8+ years of relevant industry experience, or 4+ years with a PhD, in robot controls.
Education
MS or PhD in Robotics, CS, EE, ME, or a related field (or equivalent experience).

About the job

Leads technical direction and development of humanoid robot controls, translating model-based and learning-based methods into robust capabilities deployed on physical robots.

What you'll do

  • Improve controls-stack architecture, algorithms, real-time performance, testing, and maintainability; advance whole-body control across wheeled and biped platforms.
  • Develop and deploy control capabilities including learning-based hand control, mobile manipulation, teleoperation, and estimation.
  • Set technical direction, mentor engineers, and collaborate across teams to improve robot performance, reliability, and safety.

What they ask for

  • Deep robotics fundamentals in kinematics, dynamics, state estimation, and optimization/control theory.
  • Expertise in whole-body control (WBC/OSC, QP-based control, or MPC) for floating-base or mobile systems.
  • Hands-on experience with learning-based control or reinforcement learning for robotics, including training in simulation.
  • Production-grade robot-controller development, real-time C++ and Python, and experience validating or deploying algorithms on physical robot hardware.

Nice to have

  • Experience shipping controllers to a production fleet or market at scale; dexterous/in-hand manipulation; or legged locomotion.
  • Experience with safety-critical/certified software (ISO 13849, 10218, IEC 61508).

Pay

USD 300,000 - USD 350,000 annual compensation; base salary not specified

Tools

C++, Python, RL, ISO 13849, 10218, IEC 61508

AI focus

Applies learning-based control and reinforcement learning to robotics, including training in simulation and learning-based hand control.

Model-written summary · the original posting is authoritative

First seen Oct 10, 2026 · Last verified Nov 5, 2026 (UTC)