Robotics Autonomy Engineer – Locomotion (Robotics)

Location: Irvine, California, United States; on-site

Salary: $70,000–$300,000 per year

Company

hirify.global develops risk-aware, reliable, field-ready AI systems for embodied intelligence and real-world robotics deployments.

What you will do

• Architect and implement reinforcement learning pipelines for robotic locomotion and manipulation.
• Integrate Isaac Gym, Isaac Lab, MuJoCo, or similar physics-based simulation environments with custom training workflows.
• Develop reward functions, policy architectures, domain randomization, and sim-to-real transfer methods.
• Deploy and validate locomotion behaviors on quadruped and humanoid robots across varied and unstructured terrain.
• Build GPU-accelerated simulation infrastructure and automate evaluation, domain adaptation, and reproducibility workflows.
• Collaborate with systems, perception, and embedded engineers while using telemetry and field data to improve model generalization.

Requirements

• Master’s degree or higher in Robotics, Computer Science, Engineering, or a related field; a PhD is strongly preferred.
• Deep expertise in reinforcement learning for continuous control and a strong understanding of contact dynamics, control theory, and kinematics.
• Experience with legged robot platforms and preferably 2+ years developing and deploying locomotion policies on real robotic systems.
• Proficiency with Isaac Gym, Isaac Lab, MuJoCo, PyBullet, or comparable simulation tools.
• Strong Python and/or C++ skills in Linux-based development environments.
• Familiarity with PyTorch or TensorFlow and demonstrated experience bridging the sim-to-real gap.

Nice to have

• 3+ years of experience in an industry or startup robotics setting.
• Experience with neural network controllers on resource-constrained robotic platforms and real-time onboard inference.
• Publications or open-source contributions in locomotion, reinforcement learning, or control.
• Familiarity with ROS/ROS2, manipulation, loco-manipulation, whole-body coordination, or multi-agent learning.
• Experience debugging sim-to-real issues at scale or contributing to reinforcement learning libraries and simulation platforms.

Culture & Benefits

• Work on robots operating in unstructured and previously unknown real-world environments.
• Collaborate with a technically diverse team focused on creativity, resilience, and interdisciplinary problem-solving.
• Contribute to field-deployed robotic systems and foundational models for perception, planning, localization, and manipulation.
• Inclusive workplace with employment decisions based on merit, qualifications, and performance.