SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Salary: USD 270,000 - 300,000 / annual
Niantic Spatial is building the future of physical AI, powered by a proprietary database of over 30 billion posed images. The company's mapping and Visual Positioning System technology enables precise spatial understanding for robotics, public sector, and industrial customers.
You will lead engineering for the real-to-sim product within the Embodied AI group, addressing one of the fundamental challenges in autonomy: the sim-to-real gap in visual-spatial understanding. Working alongside the group's General Manager and Product leader, you will inform the roadmap, own technical requirements, and personally prototype and evaluate proposed changes.
Key responsibilities include:
- Sharpening the roadmap by bringing first-hand knowledge of customer pain points and existing solutions to roadmap decisions
- Owning the technical requirements for the real-to-sim stack, making final recommendations on what to build, integrate, and simplify
- Designing and running reproducible evaluations with the Real-World Test Lab to measure impact on policy transfer and real-world performance
- Leading engineering delivery and personally building critical features, keeping scope tight and removing blockers
- Setting a high technical bar for the team and deepening understanding of robotics development and deployment
This role requires an entrepreneurial tech lead with a co-founder mentality who loves to build and ship, not someone who wants to manage without shipping or ship without owning commercial consequences. You will be energized by helping those around you do their best work.
REQUIREMENTS:
- Experience training, evaluating, and deploying robot policies in systems used by enterprise or government customers, with responsibility for real operating conditions
- Deep practical experience using simulation for policy training or evaluation (NVIDIA Isaac Sim, Isaac Lab, MuJoCo, or equivalent); ability to diagnose sim-to-real failures
- Hands-on experience with reinforcement learning, imitation learning, or both, and with deep-learning frameworks such as PyTorch
- Practical understanding of how visual perception and 3D scene representations affect robotics training, evaluation, and real-world performance
- Experience running experiments on real robots from hypothesis through defensible results
- Strong Python and C++ skills with experience building reliable production software
- Bachelor's degree or higher in a relevant field
NICE TO HAVE:
- Authored or maintained a public robotics benchmark
- Helped take an early product to repeatable adoption across multiple customers
- Built or substantially extended robotics simulation infrastructure (scene authoring, domain randomization, large-scale training/evaluation)
- Trained and deployed vision-based navigation or mobility policies in varied, unstructured environments
- Built pipelines that turn real-world reconstructions into simulation-ready environments
