Jobs at SpAItial AI

Conduct research on 3D generation, reconstruction, and world models. Design, implement, and evaluate state-of-the-art methods and prototypes, collaborate with the research team, present findings, and contribute to publications at leading computer vision, graphics, and machine learning conferences.

Develop and improve 3D reconstruction methods for geometry, appearance, materials, lighting, dynamic scenes, and large environments. Implement and evaluate modern scene representations such as Gaussian splats and radiance fields, optimize losses and priors, run benchmark experiments, and collaborate with research and engineering teams to productionize successful approaches.

Conduct advanced research in 3D reconstruction and novel view synthesis, covering geometry, appearance, materials, lighting, dynamics, neural rendering, and feed-forward models. Develop improved losses, priors, and optimization strategies; evaluate methods on public and internal benchmarks; and collaborate with engineering teams to productionize successful research.

Build and operate inference services and APIs for production world models. Responsibilities include deploying research models, optimizing GPU utilization, memory, batching, cold starts, reliability, and cost at scale. Collaborate with research and product teams to deliver new AI capabilities and customer-specific configurations. Requires strong Python, production API ownership, containerized GPU services, and hands-on inference performance optimization.

Own SpAItial’s design system and product experience across web and mobile surfaces. Design reusable components, interaction models, prototypes, 3D-world workflows, responsive interfaces, and mobile journeys. Collaborate closely with engineers and implement production-quality front-end experiences using React and TypeScript, while maintaining Figma libraries and documentation. The role also covers marketing and company surfaces, spatial interactions, accessibility, performance, and design-to-release refinement.

Create polished 3D prototypes, captures, videos, tutorials, launch films, and social content showcasing SpAItial’s AI models. Own organic content across X, LinkedIn, and YouTube, including strategy, publishing, community engagement, and audience growth. Collaborate with research and engineering teams, prototype emerging 3D use cases, manage creator relationships, and improve content based on performance and community feedback.

The Research Engineer will develop innovative generative 3D machine learning methods, train and optimize models, and refine 3D content generation processes, focusing on geometric accuracy and integrating physics-aware capabilities.

As a 3D Graphics & Rendering Engineer, you'll design and optimize synthetic datasets for 3D models, enhance rendering pipelines, and collaborate with research teams.

Design and develop image/video diffusion models, perform large-scale model training, maintain data for training, and optimize models for production use.

Own end-to-end training of vision-language-action and world-action robot policies, from dataset curation and model architecture through distributed training, evaluation, and deployment. Responsibilities include adapting VLM backbones for control, designing action representations, reducing the sim-to-real gap, building action-conditioned world models, and applying supervised fine-tuning and reinforcement learning. The role also contributes to technical direction for embodied AI research.

Research Scientist developing robust 3D reconstruction systems using multi-view geometry, SfM, SLAM, bundle adjustment, deep multi-view stereo, learned matching, and monocular depth. Responsibilities include designing pose estimators and reconstructors, scaling methods to real-world datasets, evaluating accuracy and quality, integrating state-of-the-art models, and collaborating on production deployment. Requires advanced computer vision research expertise, Python and PyTorch proficiency, and practical experience with COLMAP, ORB-SLAM, and Ceres.

The role involves building and maintaining ML and cloud infrastructure for training large-scale generative models. Responsibilities include designing GPU clusters, supporting distributed training, managing storage systems, and collaborating with researchers and engineers.

The role involves building and operating ML systems and infrastructure for large foundation models, data pipelines, and experiment orchestration in a collaborative environment.

Lead research on designing, building, training, and optimizing diffusion-based generative models for high-quality 3D content from diverse inputs, emphasizing world-scale scenes.