Research Intern – Video World Models (Research & ML Systems)
About The Position
We are seeking an exceptional Research Intern to join our core team in building the next generation of interactive Video World Models. While traditional generative AI focuses on generating passive pixels (e.g., text-to-video), our mission is fundamentally more ambitious: we are building foundational "World Models" that inherently understand physics, causality, action spaces, and complex dynamics directly from internet-scale data. Our goal is to train models that can simulate and "dream" complex virtual worlds, allowing users and agents to explore and interact with them in real time. This is not a purely theoretical role. Training interactive world models at this scale requires pushing the limits of modern computing power. We operate at the intersection of cutting-edge generative AI research and high-performance machine learning systems. We are looking for "full-stack" hacker-researchers—visionary thinkers who are also elite engineers, capable of co-designing novel neural architectures and engineering the highly optimized infrastructure required to train them across large-scale computing cluster.
Requirements
- Currently pursuing a PhD (or Master’s degree with a truly exceptional research/engineering track record) in Computer Science, Machine Learning, Computer Architecture, or a related field.
- Exceptional, production-level coding proficiency in Python or other languages.
- Background in competitive programming is a great plus.
- Experience with modern AI infrastructure stack and large-scale machine learning systems, such as PyTorch FSDP, Megatron, etc.
- Experience with GPU kernels using CUDA and/or Triton is a great plus.
- Thorough theoretical and practical understanding of modern generative paradigms (Diffusion, Vision Transformers, Autoregressive sequence modeling, discrete tokenization/VAEs).
- First-author publications in top-tier AI venues (NeurIPS, ICLR, ICML, CVPR, ICCV) OR premier ML Systems venues (MLSys, OSDI, ASPLOS).
Responsibilities
- Architect & Scale Foundation Models: Design, train, and scale state-of-the-art interactive world models (combining Diffusion, Autoregressive Transformers, VAEs, LLMs, VLMs) on massive video datasets.
- Push the Boundaries of ML Systems: Architect highly scalable distributed training pipelines, utilizing advanced model and data parallelism to train massive models efficiently on large-scale computing cluters.
- Optimize for Efficiency: Profile and optimize model architectures to break through memory and compute bottlenecks. Write high-performance, custom hardware kernels to maximize Model FLOPs Utilization (MFU) and enable real-time, low-latency inference.
Benefits
- 1 hour of paid sick leave for every 30 hours worked
- up to 13 paid holidays throughout the calendar year
- Company-sponsored medical plan
Stand Out From the Crowd
Upload your resume and get instant feedback on how well it matches this job.
What This Job Offers
Job Type
Full-time
Career Level
Intern
