About the Institute of Foundation Models
The Institute of Foundation Models (IFM) at MBZUAI is a research lab dedicated to meaningful foundation model research — building models from scratch, understanding them deeply, and publishing work that shapes the field. You’ll work alongside world-class researchers and engineers on problems that directly define the models we ship.
The Role
Join the PAN world model project — our effort to build world models: foundation models that simulate, predict, and interact with the physical world. As a Machine Learning Engineer, you’ll own the engineering backbone of PAN: large-scale video and simulation data pipelines, distributed training for diffusion transformers, game-engine simulation environments, and world-model integration into robotics — turning research ideas into reliable, scalable systems.
What You'll Do
- Build and maintain large-scale video and simulation data pipelines — collection, cleaning, annotation, and filtering — to support world model training.
- Develop and optimize distributed training systems for large-scale diffusion transformers and world models.
- Build interactive simulation environments (e.g., Unreal Engine, Blueprint-based gyms, game integrations) for training and evaluating world models.
- Integrate world action models / video action models into robotics systems.
- Optimize inference and serving for real-time interaction, and turn research prototypes into reliable, reproducible systems.
What We're Looking For
- BSc or above in Machine Learning, Computer Science, Robotics, or a related field, or equivalent industry experience.
- Hands-on experience with state-of-the-art video generative models and world models (e.g., Cosmos-3, LTX 2.3, Self-Forcing, Lingbot-World, or comparable systems).
- Deep expertise in at least one of the following areas:
- Full-stack data pipelines — large-scale video data pipelines and/or simulation data collection; annotation and filtering workflows for video / world model training.
- Model training & infrastructure — training large-scale diffusion transformers on large GPU clusters.
- Rendering engines & simulation — Unreal Engine and Blueprint-based gym environments, game-engine integration, building interactive simulated environments.
- World action models & robotics — world action models / video action models, action-conditioned video generation, world-model applications in robotics.
- Strong engineering expertise in deep learning frameworks such as PyTorch, with the ability to debug failures across the training/inference stack (memory issues, deadlocks, I/O bottlenecks).
- Highly proficient with modern AI coding agents and web-based coding tools (e.g., Claude Code, Codex, Cursor), and skilled at leveraging them to dramatically accelerate engineering workflows.
Nice to Have
- Experience accelerating diffusion model inference (distillation, few-step generation, real-time interactive generation).
- Practical experience with web scraping and crawling frameworks (e.g., scrapy, playwright, selenium) for web-scale data curation.
- Experience with Unreal Engine C++/Blueprint development or other game-engine programming.
- Experience deploying world models in robotics or embodied-AI settings.
Skills Required
- MSc or PhD in Machine Learning or Computer Science, or equivalent industry experience
- Proficient in data collection, cleaning, and transformation at scale for multimodal datasets (video, audio, text)
- Practical experience with web scraping and crawling frameworks (Scrapy, Selenium, Playwright, BeautifulSoup)
- Experience in large-scale model training (LLMs or diffusion models) on large clusters
- Hands-on experience with state-of-the-art video generative models (e.g., Sora, Veo2, MovieGen, CogVideoX)
- Experience building and optimizing large-scale video data pipelines
- Experience accelerating diffusion model inference for improved efficiency
- Strong systems and engineering expertise in deep learning frameworks such as PyTorch
- Demonstrated ability to solve complex system-level challenges and debug failures across the training/inference stack (memory issues, deadlocks, I/O bottlenecks)
- Exceptional problem-solving and troubleshooting skills
- Strong communication and collaboration skills for effective cross-functional teamwork
What We Do
First a passion, then an idea transformed into success – when it comes to pioneering automation and digitalisation technology, the ifm group is the ideal partner. Since its foundation in 1969, ifm has developed, produced and sold sensors, controllers, software and systems for industrial automation and for SAP-based solutions for supply chain management and shop floor integration worldwide. As one of the pioneers of Industry 4.0, ifm develops and implements consistent solutions to digitalise the entire value chain “from sensor to ERP”. Today, the second-generation family-run ifm group has more than 8,750 employees and is one of the worldwide market leaders. The group combines the internationality and innovative strength of a growing group of companies with the flexibility and close customer contact of a medium-sized company.
