Spatial AI Engineer - Real‑Time 3D Vision & Simulation

Schemata; San Francisco (CA); Hybrid; USD 140,000 - 200,000; Full time

Benefits offered by this job

Competitive salary

Equity stake

Comprehensive health coverage

401(k) plan

Paid parental leave

Job summary

Schemata is building spatial intelligence platforms that turn complex 3D data into actionable world models for advanced simulation and training. We seek a Spatial Computing Engineer to own end-to-end development from research prototypes to production inference, ensuring real-time understanding of diverse environments.

You will work across cross‑functional teams, shaping 3D scene understanding with cutting‑edge AI, while profiling performance and scaling across GPUs and cloud/edge targets.

Qualifications

• PhD or 4+ years depth in 3D computer vision, robotics perception, graphics-ML or related field.
• Strong Python with deep-learning frameworks (PyTorch); confident in CUDA or compute-shader programming.
• Hands-on with 3D data types: point clouds, meshes, NeRF/LERF representations, SLAM or occupancy networks.
• Solid grounding in linear algebra, geometry and numerical optimization.
• Demonstrated ability to convert research into reliable, maintainable production code and services.

Responsibilities

• Design data pipelines that convert heterogeneous 3D assets into unified scene-graphs and knowledge graphs.
• Integrate multimodal foundation models with spatial data for diagnostics and autonomous evaluation.
• Implement GPU-accelerated training/inference and synthetic-data generation in cloud and edge environments.
• Collaborate with graphics and product engineers to ship mission-critical features blending neural perception with real-time rendering.
• Profile and optimize performance across varied hardware configurations for fidelity, latency and memory.
• Publish internally, attend CVPR/NeurIPS/SIGGRAPH and translate research into production capabilities.

Skills

Python

PyTorch

CUDA

3D computer vision

NeRF/LERF

SLAM

Real-time rendering

Education

PhD or 4+ years depth in 3D CV/graphics-ML

Tools

CUDA Toolkit

Compute Shaders

Cloud/Edge deployment

Job description

Schemata is building spatial intelligence platforms that turn complex 3D data into actionable world models for advanced simulation and training. We seek a Spatial Computing Engineer to own end-to-end development from research prototypes to production inference, ensuring real-time understanding of diverse environments.

You will work across cross‑functional teams, shaping 3D scene understanding with cutting‑edge AI, while profiling performance and scaling across GPUs and cloud/edge targets.