Your CharterBuild and maintain the simulation environments and real-time infrastructure that accelerate robot learning at 1X, reducing dependence on physical robot evaluations, scaling synthetic data production, and ensuring policies trained in simulation transfer reliably to real hardware. This is critical-path infrastructure: the AI team's iteration speed, the hardware team's ability to prototype, and the quality of training data all depend on simulation environments that are physically realistic, fast, correct, and well-maintained. You will own both the environments themselves and the systems that make them useful at scale.
Key Outcomes- Deliver diverse, physically realistic simulation environments for NEO that enable the AI team to develop and evaluate new policies without requiring real robot time for every iteration
- Measurably narrow the sim-to-real gap through domain randomization, calibration, and environment fidelity improvements, such that policies trained in simulation transfer reliably to deployed hardware
- Scale synthetic data production to meet the AI team's training needs, with infrastructure that generates diverse, high-quality simulation data efficiently and reproduces environments reliably
- Enable the hardware team to prototype and virtually test new robot hardware in simulation before manufacturing, reducing design iteration cycles and surfacing issues earlier
Key Competencies- Physics simulation depth understanding what makes a simulator physically accurate and computationally tractable; knows how to tune contact dynamics, articulated body models, and rendering fidelity for robot learning applications
- Sim-to-real instincts having practical experience narrowing the gap between simulated and real behavior; knows which differences matter for policy transfer and which can be addressed through domain randomization
- Performance-oriented engineer optimizing physics and rendering pipelines to maximize simulation throughput; thinks carefully about the tradeoff between fidelity and speed for different use cases
- Rigorous infrastructure builder writing tested, maintainable simulation code that other teams can depend on; treats correctness and reliability of the simulation stack as a first-class engineering concern
Minimum Requirements- 4+ years of experience programming in Python, C++, or similar languages, with experience building environments or benchmarks using robotics simulators (MuJoCo, PyBullet, Isaac Sim, or equivalent)
- Experience improving the performance of physics simulators or OpenGL rendering pipelines
- Strong testing practices for simulation stacks used in robot learning-comfortable writing tests that verify physical correctness and catch regressions
- Advanced degree (MS or PhD) in Computer Science or a related field
Preferred Skills- Knowledge of extrinsic and intrinsic calibration algorithms for robotics, and experience using calibration to improve sim-to-real fidelity
- Experience with domain randomization, procedural environment generation, or other techniques for scaling diverse simulation data production
- Familiarity with differentiable simulation or GPU-accelerated physics (Warp, JAX-based simulators) for high-throughput parallel training
- Background in legged locomotion, dexterous manipulation, or contact-rich robotics where simulation accuracy is most critical
Compensation$200,000 - $280,000 + Equity
Benefits- Comprehensive medical, dental, and vision coverage
- Generous paid time off, company holidays, and parental leave
- 401(k) plan with company match (100% on the first 3% of contributions, 50% on the next 2%)
- Flexible Spending Accounts (FSA) and Health Savings Accounts (HSA) options
- Commuter benefits (transit and parking)
- Short-term and long-term disability, and life insurance
- Employee Assistance Program (EAP) for mental health, financial, and personal support
- Onsite snacks and catered lunches
