SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the

simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our

world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with

physically-grounded 3D environments.

We're looking for bold, innovative individuals driven by a passion for pushing the boundaries of generative 3D AI. You should

thrive in an environment where creativity meets technical challenge and be fearless in tackling the hardest problems in 3D world

modeling. Our team is built on a foundation of dedication and a shared commitment to excellence, so we value people who take

immense pride in their work and place the collective goals of the team above personal ambition. As a part of SpAItial, you'll be

at the forefront of building World Models that bridge generative AI and the physical world. If you're ready to make an impact,

embrace the unknown, and collaborate with a talented group of visionaries, we want to hear from you.

We're seeking a Research Engineer to develop cutting-edge generative methods that create physically-grounded 3D environments. You

will work on building, training, evaluating, and optimizing models that generate high-quality 3D content from images, video, and

other inputs—with a focus on world-scale scenes that understand geometry, physics, and spatial consistency. This role is ideal for

early-career engineers who have strong fundamentals in machine learning and 3D data processing, are passionate about generative

models, and want to help define the next generation of World Model systems.

Responsibilities

Design and develop cutting-edge generative 3D machine learning methods for creating high-quality 3D content from images, video,

and other inputs.

Build, train, optimize, evaluate models for 3D reconstruction, novel view synthesis, and world generation.

Implement and experiment with state-of-the-art 3D representations including point clouds, meshes, and 3D Gaussian Splatting.

Develop training pipelines and loss functions that improve geometry accuracy, visual fidelity, and consistency.

Collaborate with researchers to integrate physics-aware priors and world model capabilities into generative systems.

Analyze model performance, debug failure cases, and iterate rapidly to improve quality and robustness.

Key Qualifications

Bachelor's or Master's degree, or equivalent project/research experience, in computer science, machine learning, computer

vision, graphics, robotics, or a related field.

Strong fundamentals in deep learning and generative models, in particular diffusion models and transformers.

Solid understanding of 3D processing concepts such as camera geometry, depth, reconstruction, point clouds, meshes, or Gaussian

splats.

Proficiency in Python and deep learning frameworks such as PyTorch, with experience in model training and optimization.

Ability to implement research papers, run experiments, and iterate quickly on new ideas.

Strong coding skills and passion for building reliable, scalable ML systems.

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.

Roll

Research Engineer - 3D World Models

Plats

London

Publicerad

24 mars

Sista ansökningsdag

16 augusti

Taggar för det här jobbet

Python AI Machine Learning

Liknande jobb

Research Engineer - Graphics

SpAItial

London•Publicerad: 5 feb.•Sista ansökan: 16 aug.

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and the simulation of reality. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments. We are looking for a research engineer with a deep graphics understanding to bridge the gap between high-end rendering and frontier AI. You will lead the creation of the synthetic engines that power our models, designing scalable pipelines that generate the ground-truth reality for our next-generation world models. If you are a graphics expert who wants to move beyond visual effects and start building the training grounds for world Intelligence, we want you on our team. Responsibilities * Design and architect high-fidelity synthetic data engines to train large-scale World Models. * Develop and scale automated rendering pipelines to generate diverse, physically-consistent 3D environments. * Integrate and refine rendering workflows using tools like Blender, Unity, 3DMax, or equivalent platforms. * Work with our world-class research team to ensure datasets and synthetic data workflows align with our world model training objectives. Key Qualifications * Strong background in computer graphics with a proven track record of building complex rendering systems or high-fidelity simulation environments. * Deep understanding of 3D representations (meshes, voxels, point clouds, implicit surfaces, etc.); knowledge in 3D Gaussian Splatting and volumetric rendering is a nice to have. * Proficiency in Blender, Unity, Unreal Engine, 3DMax, or similar rendering and simulation software. * Bachelor’s, Master’s, or equivalent experience in computer science, graphics, or related fields. * Nice to have: experience, or ambition to work with procedural generation tools and techniques. * Background in large-scale data workflows for AI/ML model training. 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.

Machine Learning & Cloud Infra Engineer

SpAItial

London•Publicerad: 14 apr.•Sista ansökan: 16 aug.

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and simulation. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments. We’re looking for bold, innovative individuals driven by a passion for tackling hard problems in generative 3D AI. You should thrive in an environment where creativity meets technical challenge, take pride in craft, and collaborate closely with a small team building frontier systems. We are seeking a Machine Learning & Cloud Infra Engineer to build and own the infrastructure that powers our World Model research and productization. You will design, implement, and operate scalable training and data systems for large diffusion-based generative models, spanning GPU clusters, storage, orchestration, and reliable model serving. This role is hands-on and systems-focused, enabling researchers and engineers to train, evaluate, and deploy world-scale models efficiently and safely. Responsibilities * Own and evolve the ML + cloud infrastructure that enables training and evaluation of massive foundation models. * Design and operate GPU clusters: Provision, scale, and maintain multi-node, multi-GPU training environments (on cloud and/or on-prem), including scheduling, quotas, and capacity planning. * Distributed training enablement: Support high-throughput training stacks (e.g., PyTorch DDP/FSDP, NCCL) and ensure performance, stability, and reproducibility across large runs. * Storage and data throughput: Build and optimize storage systems and networking for petabyte-scale datasets and high-bandwidth training (object storage, NVMe, shared filesystems, caching, data locality). * Containerization and orchestration: Package and deploy workloads with Docker and Kubernetes (or comparable systems); maintain infrastructure-as-code (Terraform) and reliable release processes. * Observability and reliability: Implement monitoring, logging, and alerting for cluster health, job performance, and cost; define SLOs and on-call/incident response practices. * Security and access: Manage secrets, IAM, and secure network boundaries for research and production systems. * Collaboration: Partner closely with ML researchers and engineers to unblock training, iterate on tooling, and improve developer experience. * Production pathways: Support model evaluation and serving infrastructure where needed, and ensure smooth transitions from research to deployable systems. Key Qualifications: * 3+ years of professional experience in infrastructure, platform, or cloud engineering (ML infrastructure experience strongly preferred). * Hands-on experience with GPU compute and performance debugging (CUDA/NCCL concepts, GPU utilization, networking bottlenecks, profiling). * Strong experience operating cloud environments (AWS, GCP, or Azure), including networking, IAM, and cost management. * Proficiency with containers and orchestration (Docker, Kubernetes) and infrastructure-as-code (Terraform). * Strong scripting and automation skills (Python plus Bash/PowerShell). * Familiarity with distributed training and modern ML stacks (PyTorch; DDP/FSDP or comparable). * Experience with monitoring and observability tooling (Prometheus/Grafana, OpenTelemetry, ELK, or similar). * Experience building CI/CD for infra and ML workflows (e.g., CircleCI, GitHub Actions). 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.

PythonAWSAzure

Machine Learning Systems & Infrastructure Engineer

SpAItial

London•Publicerad: 7 maj•Sista ansökan: 16 aug.

SpAItial is pioneering the next generation of World Models, pushing the boundaries of generative AI, computer vision, and simulation. We are moving beyond 2D pixels to build models that natively understand the physics and geometry of our world. Our mission is to redefine how industries, from robotics and AR/VR to gaming and cinema, generate and interact with physically-grounded 3D environments. We’re looking for bold, innovative individuals driven by a passion for tackling hard problems in generative 3D AI. You should thrive in an environment where creativity meets technical challenge, take pride in craft, and collaborate closely with a small team building frontier systems. We are seeking a Machine Learning Systems & Infrastructure Engineer to build and own the systems that turn raw real-world data into trained world models and reliable production endpoints. You will design, implement, and operate scalable training stacks, data ingestion pipelines, experiment orchestration, and model serving for large diffusion-based generative models. The role is hands-on and code-heavy — you will work inside the same monorepo as the research team, mostly in Python, and should be as comfortable refactoring a trainer class or a dataset loader as you are writing Terraform. RESPONSIBILITIES * Own and evolve the ML systems that enable training, evaluation, and serving of large foundation models — trainer, dataset loaders, checkpointing, and experiment orchestration code. * Distributed training enablement: Improve high-throughput training stacks (e.g., PyTorch DDP/FSDP, NCCL) for performance, stability, and reproducibility, including preemption-safe and sharded checkpointing. * Data systems and pipelines: Build end-to-end Python pipelines that turn third-party capture sources into clean, versioned training datasets — including scraping (e.g., Playwright) and preprocessing — and optimize the underlying storage at petabyte scale (object storage, fuse mounts, caching layers, shared filesystems, and relational / analytical / embedded metadata stores). * ML workflow orchestration and serving: Operate the systems researchers use to launch experiments, data jobs, and production endpoints — workflow engines (e.g., Kubeflow Pipelines, Airflow), GPU schedulers (e.g., Volcano, Slurm), experiment trackers (e.g., MLflow, Weights & Biases), and managed-inference platforms (e.g., Modal, Triton) — and maintain a launcher SDK for one-command runs. * Containerization and packaging: Ship workloads with Docker and Kubernetes; maintain IaC (Terraform) for the surfaces you own and CI/CD pipelines, including self-hosted GPU runners. * Observability and reliability: Monitoring, logging, and alerting for job performance, data-pipeline health, and cost (e.g., Prometheus/Grafana, OpenTelemetry); define SLOs and incident response for the systems you own. * Security and access: Manage secrets, IAM, and network boundaries (e.g., Tailscale, cloud VPC) for the systems you own. * Collaboration: Partner with ML researchers, engineers, and the platform team to unblock training and data work and improve developer experience. KEY QUALIFICATIONS * 3+ years writing production-quality Python in a large, multi-author codebase, with strong SWE fundamentals (ML systems experience strongly preferred). * Hands-on with modern ML training stacks (PyTorch; DDP/FSDP or comparable); have personally debugged distributed jobs across many GPUs and nodes. * Have shipped non-trivial end-to-end data pipelines at scale — ingestion, transformation, validation, versioning, republish — ideally including real-world sources with rate limits, auth, or undocumented APIs. * Hands-on GPU compute and performance debugging (CUDA/NCCL, GPU utilization, networking bottlenecks, profiling). * Working knowledge of cloud environments (AWS, GCP, or Azure), including object storage, IAM, and cost awareness. * Proficient with containers (Docker, Kubernetes) and comfortable reading and writing IaC (Terraform) for the surfaces you ship. * Strong working knowledge of how to store and query large datasets at scale: SQL fundamentals; relational (e.g., Postgres), analytical (e.g., BigQuery, Snowflake), and embedded (e.g., SQLite) stores; and object storage with caching layers. Familiarity with ML workflow orchestration and experiment tracking (e.g., Kubeflow Pipelines, MLflow). * Experience with monitoring and observability tooling (e.g., Prometheus/Grafana, OpenTelemetry) and CI/CD for infra and ML workflows (e.g., GitHub Actions). 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. 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.

PythonAWSAzure