Staff Engineer – Robot Learning, Embodied AI

Niantic Spatial, Inc.

. Lead engineering for Niantic Spatial's real-to-sim product within the Embodied AI group .

Posted 10/2/2026full-timeSan Francisco • California • United StatesLead💰 $270,000 - $300,000 per yearWebsite

Core Competencies

Role fit

Core Competencies

Use this summary to align your resume positioning with the role.

Demonstrates expertise in robotics development and deployment, with a strong focus on training and evaluating robot policies using simulation tools. Proficient in Python and C++, with hands-on experience in reinforcement learning and deep-learning frameworks.

Highest-signal resume keywords

Robotics DevelopmentSimulation for Policy TrainingReinforcement LearningDeep-Learning FrameworksPerformance Evaluation

ATS Keywords

Tailor your resume

Applicant Tracking System Keywords

Tip: use these terms in your resume and cover letter to boost ATS matches.

Hard Skills

PythonC++Reinforcement LearningImitation LearningSimulation ToolsPolicy EvaluationDeep-Learning FrameworksVisual Perception3D Scene RepresentationsProduction Software Development

Soft Skills

CollaborationProblem-SolvingLeadership

Tools & Technologies

NVIDIA Isaac SimIsaac LabMuJoCo

Certifications & Qualifications

Bachelor's Degree or Higher

Industry Keywords

Enterprise RoboticsGovernment RoboticsReal-World PerformancePolicy TransferCustomer Value

Tech Stack

Tools & technologies

PythonPyTorchC++

About the role

Key responsibilities & impact

Lead engineering for Niantic Spatial's real-to-sim product within the Embodied AI group
Inform the product roadmap using firsthand knowledge of customer pain, existing solutions, and customer value
Own technical requirements and guide pragmatic design of the real-to-sim stack
Make final recommendations on what to build, integrate, and simplify
Ensure capabilities work within customers' existing training and evaluation workflows
Design and run reproducible evaluations with the Real-World Test Lab
Measure the impact of the real-to-sim stack on policy transfer and real-world performance against customers' existing approaches
Lead engineering delivery and personally build critical features
Keep scope tight, remove blockers, and deliver performant capabilities to customers quickly
Set a high technical bar and deepen the team's understanding of robotics development and deployment
Collaborate with the group's General Manager, Product leader, researchers, engineers, and customers

Requirements

What you’ll need

Experience training, evaluating, and deploying robot policies in systems used by enterprise or government customers, with responsibility for performance in real operating conditions
Deep practical experience using simulation for policy training or evaluation, including NVIDIA Isaac Sim, Isaac Lab, MuJoCo, or equivalent
Experience diagnosing sim-to-real failures and understanding when greater fidelity improves outcomes
Hands-on experience with reinforcement learning, imitation learning, or both
Experience with deep-learning frameworks such as PyTorch
Practical understanding of visual perception and 3D scene representations in robotics training, evaluation, and real-world performance
Experience running experiments on real robots from hypothesis through defensible results
Strong Python and C++ skills
Experience building reliable production software
Bachelor's degree or higher in a relevant field
Able to work in the San Francisco office three days per week
Authorized to work without restrictions in the country where the position is based
Must be willing to address employment sponsorship requirements for the country where the job is based

Benefits

Comp & perks

Annual bonus
Equity
Comprehensive benefits package
Medical coverage
Dental coverage
Vision coverage
401(k)
Relocation assistance may be available, as indicated by the application form