Staff Simulation Architect - Core Simulation Platform

At the core of every robot policy we ship is a simulation platform that has to be fast enough for RL training, accurate enough for controls validation, and stable enough to be the team's daily driver. As Staff Software Architect for Core Simulation Platform, you'll own the architecture of that platform — the distributed systems, performance engineering, and large-scale infrastructure decisions that let it run millions of parallel experiences a day. You don't need a deep robotics or simulation background to thrive here: what matters most is a track record of architecting complex, high-performance, distributed software systems. We'll pair you with senior team members who bring domain depth in physics and robotics.

• →Own the architecture of the core simulation platform — high-performance distributed systems that serve as the foundation for policy training, controls validation, and CI/CD integration testing.
• →Design and drive the build-out of cloud-native pipelines capable of generating millions of experience hours per day, architecting how compute-heavy workloads parallelize and scale for rapid iteration.
• →Define the platform's core abstractions and APIs, ensuring the system stays extensible as new physics, sensor, and rendering capabilities are added by domain specialists.
• →Set technical direction on performance, reliability, and scalability, identifying and resolving systemic bottlenecks in a large, high-throughput distributed system.
• →Define the platform roadmap and review major design proposals, ensuring improvements visibly reduce iteration time for RL, controls, and perception teams.
• →Partner with Controls, AI Research, and Perception leadership to translate their evolving needs into a coherent, extensible architecture as the platform grows.
• →Establish architectural standards and mentor senior engineers on system design, bringing outside experience in distributed systems and software architecture into a robotics context.

• Excellent C++ and/or Python programming skills, with a strong track record of applying them to large-scale system architecture
• Deep experience architecting distributed, high-throughput, or real-time software systems — this experience can come from robotics, gaming, simulation, high-frequency trading, large-scale backend infrastructure, or similar domains
• Proven experience architecting workloads on cloud platforms (AWS, GCP, Azure) with distributed computing frameworks (e.g., Ray, Kubernetes)
• Deep familiarity with software development best practices: CI/CD, automated testing, and code quality standards
• Track record of making and defending architectural trade-offs (performance vs. flexibility, latency vs. throughput) and communicating them clearly to engineers and leadership
• Comfort ramping up quickly in a new technical domain, and partnering closely with subject-matter experts in physics, robotics, and ML to translate their needs into system design

• Prolonged periods of sitting at a desk and working on a computer
• Must be able to lift 15 pounds at times
• Vision to read printed materials and a computer screen
• Hearing and speech to communicate

• Understanding of robotics concepts: kinematics, dynamics, controls, system identification
• Experience with modern robotic simulators (Isaac Lab, MuJoCo, or equivalent)
• Understanding of Reinforcement Learning, with research or production experience

• Bachelor's, Master's, or PhD in Computer Science, Engineering, or related field (or equivalent experience)
• 7+ years of software engineering experience, including significant time in a software architecture or technical leadership role on complex, large-scale systems