SpAItial is pioneering the development of a frontier 3D foundation model, pushing the boundaries of AI, computer vision, and spatial computing. Our mission is to redefine how industries, from robotics and AR/VR to gaming and movies, generate and interact with 3D content.
We’re seeking a Machine Learning Research Engineer to design, test, and refine high-impact experiments for training our 3D foundation model. You’ll run targeted ablations, implement promising research ideas, and integrate your findings into production-scale pipelines.
Responsibilities
Design and run ablation experiments to improve model performance.
Evaluate new research papers and implement them on our data
Incorporate experiment findings into our training pipelines.
Collaborate with research and engineering teams to maintain strong baselines.
Key Qualifications
Experience evaluating training runs at different scales (data size, format types, etc.)
Ability to fine-tune models with various settings (e.g., ablating different estimators for depth, normals)
Skill in evaluating research papers and implementing them with our data
Proficiency in Python and ML frameworks (e.g., PyTorch, TensorFlow, JAX).
Bachelor’s, Master’s, or equivalent experience in Computer Science, Machine Learning, or a related field.
Preferred Qualifications
Familiarity with 3D representation learning (e.g., NeRF, Gaussian Splatting).
Procedural generation toolkit
Understanding of generative modeling (e.g., VAEs, GANs, transformers).
Background in working with large-scale data and such as those used for GenAI training
Contributions to open-source generative AI projects or relevant publications.
At SpAItial, we are committed to creating a diverse and inclusive workplace. We welcome applications from people of all backgrounds, experiences, and perspectives. We are an equal opportunity employer and ensure all candidates are treated fairly throughout the recruitment process.
Top Skills
What We Do
SpAItial is pioneering Spatial Foundation Models (SFMs), a groundbreaking AI paradigm designed to generate and reason about the appearance and physics of real and imagined environments. SFMs possess an intrinsic understanding of space-time, enabling transformative shifts in applications at the intersection of virtual and physical worlds.
Unlike existing generative AI technologies such as LLMs, image, or video models, SFMs operate natively in physical space. This significantly advances their cognitive capabilities, which mimics human understanding. SFMs promise to revolutionize various applications across industries, from creating immersive virtual worlds for gaming and entertainment, to advancing CAD engineering and construction, to powering next-generation VR/AR experiences, and enabling sophisticated, physically-intelligent robotics.
