Tech Stack

Description

You will architect and maintain large-scale simulation infrastructure for Apollo, a general-purpose humanoid robot, ensuring virtual testing accurately mirrors real-world performance. You'll build scalable frameworks, automated pipelines, and HPC cloud orchestration to support locomotion, manipulation, and synthetic data collection.

Requirements

• Bachelor's or Master's in CS, Engineering, or related field
• Minimum 5 years professional experience in simulation or infrastructure engineering
• Expertise in robotics simulation tools (IsaacSim/IsaacLab, MuJoCo, Gazebo, Omniverse)
• Proficiency with monitoring dashboards (Grafana)
• Experience with GPU-accelerated HPC on cloud/on-prem; advanced Python or C++

Responsibilities

• Architect and implement scalable, high-fidelity humanoid simulation frameworks
• Deploy and manage HPC clusters (GCP, on-prem) for sub-24-hour turnaround on simulation requests
• Establish observability and monitoring for simulation health and performance
• Develop custom tools and dashboards (Python, Grafana, FastAPI/Dash) for visualizing simulation results
• Create automated ETL pipelines for large-scale training data and performance benchmarking