Simops Engineer

Apptronik Apptronik · Robotics · HQ · Software Engineering

Apptronik is seeking a SimOps Engineer to architect and maintain large-scale simulation infrastructure for their humanoid robot, Apollo. This role involves applying high-fidelity simulation to robotics, managing virtual environments for locomotion, manipulation, and synthetic data generation, and building scalable frameworks for system optimization and reliability analysis.

What you'd actually do

  1. Architect and implement scalable, highly-available simulation frameworks. These should support high-fidelity humanoid dynamics, including complex joint interactions and balance controllers, while enabling domain randomization and synthetic data generation.
  2. Deploy and manage High-Performance Computing (HPC) clusters (e.g., GCP, on-prem) to enable sub-24-hour turnaround for massive, ad-hoc simulation requests and parallelized training workloads.
  3. Establish robust observability and monitoring to provide insight into simulation health, utilization, and performance.
  4. Develop specialized tools and dashboards (e.g., using Python, Grafana, FastAPI, or Dash) to visualize complex simulation results that require custom interaction or specialized plotting.
  5. Create automated pipelines to extract, transform, and load (ETL) simulation data for large-scale training and performance benchmarking.

Skills

Required

  • Robotics Simulation: Expertise in tools such as IsaacSim/IsaacLab, MuJoCo, Gazebo, Omniverse.
  • Monitoring & Dashboards: Proficiency with tools like Grafana for infrastructure and telemetry visualization.
  • High-Performance Computing: Demonstrated experience managing GPU-accelerated HPC clusters on cloud platforms (e.g., AWS/GCP) or on-prem systems.
  • Advanced Python or C++ skills
  • Hands-on experience with GitLab, Jenkins, or GitHub Actions for automating software builds and simulation testing.
  • Comfort deploying IaC using tools like Kubernetes, Helm, Terraform, Ansible, Docker.
  • Proven ability to conduct system-level optimization for complex robotic architectures to identify high-performance hardware/software solutions.
  • Bachelor's or Master's degree in Computer Science, Engineering, or a related technical field.
  • Minimum of 5 years of professional, full-time experience in simulation or infrastructure engineering, with a track record of improving simulation through automation.

Nice to have

  • experience with web frameworks for building internal research tools is a plus
  • experience with ROS/ROS2 is a plus

What the JD emphasized

  • high-fidelity simulation rigor
  • scalable frameworks
  • automated pipelines
  • system-level optimization
  • reliability analysis
  • humanoid dynamics
  • domain randomization
  • synthetic data generation
  • HPC clusters
  • parallelized training workloads
  • observability and monitoring
  • automated data pipelines
  • Simulation-in-the-loop Testing
  • system-level optimization

Other signals

  • humanoid robotics
  • embodied AI
  • simulation infrastructure
  • synthetic data collection
  • system-level optimization