Niantic Spatial
Staff Engineer - Robot Learning, Embodied AI
$270K–$300K
San Francisco, CA · Hybrid · Staff · Full-time · Posted Oct 2, 2026
- Education
- Bachelor's degree or higher in a relevant field.
About the job
Lead engineering for a real-to-sim product that helps autonomy teams train and evaluate embodied AI, owning technical direction, customer impact, and delivery.
What you'll do
- Inform the roadmap and set technical requirements for the real-to-sim stack.
- Design and run reproducible evaluations of policy transfer and real-world performance.
- Lead engineering delivery and personally build critical features.
What they ask for
- Experience training, evaluating, and deploying robot policies in enterprise or government customer systems, with responsibility for real-world performance.
- Practical simulation experience for policy training or evaluation, including diagnosing sim-to-real failures.
- Hands-on experience with reinforcement learning or imitation learning and deep-learning frameworks such as PyTorch.
- Strong Python and C++ skills; production software experience; bachelor's degree or higher in a relevant field.
Nice to have
- Authored or maintained a public robotics benchmark.
- Built or substantially extended robotics simulation infrastructure, or pipelines that turn real-world reconstructions into simulation-ready environments.
Pay
USD $270,000 – $300,000 per year (base salary)
Tools
NVIDIA Isaac Sim, Isaac Lab, MuJoCo, PyTorch, Python, C++
AI focus
Build and evaluate a real-to-sim stack for embodied AI, improving robot policy transfer and visual-spatial understanding in real-world conditions.
Model-written summary · the original posting is authoritative