Research Scientist - The Diffusion LLM Team
$150k - $400k • Sunnyvale, CA • Full-time
Posted 5mo ago
Remote Work Policy
On-site
Employment Type
Full-time
Categories
LLM Engineer
About the job
The Institute of Foundation Models is a dedicated research lab focused on building, understanding, using, and risk-managing foundation models. Our mission is to advance research, nurture the next generation of AI builders, and drive transformative contributions to a knowledge-driven economy. As a member of the Diffusion LLM Team, you will play a central role in designing, building, and releasing industrial-scale Diffusion Large Language Models. This involves developing and releasing diffusion-based LLMs that push the speed-quality frontier at scale, matching autoregressive model quality while enabling faster generation, and improving inference-time scaling relative to standard LLMs. You will collaborate closely with researchers and engineers across architecture, training, and infrastructure to translate research ideas into high-impact model releases for next-generation LLMs.
Responsibilities
- Design, train, and scale large language models for research and real-world deployment.
- Lead or contribute to the release of industrial-scale diffusion language models.
- Develop and evaluate training strategies and objectives for efficient model scaling.
- Publish research findings and contribute to open-source model and code releases.
Requirements
- MSc or PhD in Machine Learning or Computer Science, or equivalent industry experience.
- Hands-on experience training large models using modern deep learning frameworks at scale.
- Strong background in transformer architectures and large-scale optimization techniques.
- Demonstrated expertise in LLM pre-training or post-training, with a strong focus on model scaling.
- Research track record evidenced by publications, open-source contributions, or released models.
- Knowledge of diffusion models or discrete diffusion methods is a plus.
- Ability to work independently while contributing effectively to a collaborative research team.