Spatial Computing Engineer

Schemata; San Francisco (CA); On-site; USD 190,000 - 280,000; Full time

Benefits offered by this job

Competitive equity

Top-tier benefits

In-person SF culture

Job summary

Schemata in San Francisco is hiring a Spatial Computing Engineer to design and optimize 3D scene-understanding systems and multimodal AI pipelines. You will drive end-to-end work from research prototypes to production inference, targeting real-time responses across diverse deployment targets.

You will collaborate with graphics and product engineers to ship mission-critical features, profile GPU workloads, and push the boundaries of 3D perception, robotics, and neural rendering in regulated

Qualifications

• PhD or equivalent depth in 3D CV, robotics perception, graphics-ML.
• Strong Python with DL frameworks (PyTorch).
• Hands-on with 3D data types: point clouds, meshes, NeRF/LERF representations.

Responsibilities

• Research and prototype state-of-the-art methods for 3D reconstruction and world-model learning.
• Design pipelines to convert CAD, LiDAR, and sim outputs into scene graphs.
• Integrate multimodal models with spatial data for diagnostics and evaluation.
• Implement GPU-accelerated training/inference and large-scale evaluation.
• Collaborate with graphics and product engineers to ship features.
• Profile and optimize performance across hardware for latency/memory balance.
• Publish internally and contribute to CVPR/NeurIPS/SIGGRAPH activities.

Skills

PhD or 4+ years experience

3D computer vision

PyTorch

CUDA programming

Spatial data structures

Education

PhD or equivalent in 3D vision / robotics

Tools

CUDA

Compute shaders

GLSL

Job description

About the Role

We are seeking a highly skilled Spatial Computing Engineer to join our team full‑time. You will play a foundational role in designing, building and optimizing the 3D‑scene‑understanding systems and multimodal AI pipelines that turn raw spatial data into actionable world‑models for next‑generation simulation and training applications.

This is a high‑impact, cross‑functional role: you will work end‑to‑end from cutting‑edge research prototypes to production inference and performance profiling, ensuring our applications understand complex environments and respond in real time across diverse deployment targets.

About Schemata

At Schemata, we are transforming the $400 B virtual‑training and simulation market by fusing 3D computer vision, neural rendering and large multimodal models inside highly regulated industries. Our platform delivers photorealistic, intelligent 3D experiences, demanding robust spatial reasoning, high‑performance data pipelines and seamless integration between traditional graphics and AI‑driven perception.

Core Responsibilities

• Research and prototype state‑of‑the‑art methods for 3D reconstruction, segmentation, spatial reasoning and world‑model learning (e.g., NeRF/LERF‑style multimodal models).

• Design data pipelines that convert heterogeneous 3D assets (CAD, photogrammetry, LiDAR, simulation output) into unified, queryable scene‑graphs and knowledge graphs.

• Integrate multimodal foundation models (LLMs, VLMs) with spatial data to power diagnostics, step‑by‑step instruction and autonomous evaluation in virtual‑training scenarios.

• Implement GPU‑accelerated training/inference, synthetic‑data generation and large‑scale evaluation workflows in cloud and edge environments.

• Collaborate with graphics and product engineers to ship mission‑critical features that blend neural perception with real‑time rendering.

• Profile and optimize performance across varied hardware configurations, balancing fidelity, latency and memory.

• Publish internally, attend CVPR / NeurIPS / SIGGRAPH, and translate the latest research into production capabilities.

Essential Skills & Experience

• PhD or 4 + years equivalent 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.

• Experience profiling GPU workloads and scaling distributed training or real‑time inference pipelines.

Nice to Have

• Tier‑1 conference publications (CVPR, NeurIPS, SIGGRAPH) or open‑source contributions in 3D AI.

• Large‑scale data‑engineering / MLOps experience for 3D pipelines.

• Reinforcement‑learning or embodied‑AI background.

• Defense, aerospace or other regulated‑industry experience; active or ability to obtain U.S. security clearance.

Why Join Us?

• Own & shape the spatial‑intelligence function at the frontier of multimodal AI and 3D simulation.

• Tackle cutting‑edge problems combining 3D perception, graphics and neural rendering to save lives and billions of dollars.

• Work with world‑class researchers in a fast‑paced, high‑ownership environment where your innovations ship directly to mission‑critical users.

• Competitive upside, meaningful equity, top‑tier benefits and whatever gear you need to excel, with an in‑person culture in San Francisco and flexibility for extraordinary talent.