Responsibilities
- Develop efficient algorithms and architectures for large-scale generative and multimodal models.
- Build and advance distillation frameworks, including step distillation and classifier-free guidance distillation.
- Apply quantization, model acceleration, and hardware-efficient inference methods to improve model efficiency.
- Advance scalable diffusion and autoregressive generative modeling for image generation, video generation, and vision-language applications.
- Develop methods and infrastructure for transferring foundation-model capabilities into smaller, more efficient models for scalable training, optimization, and deployment.
Requirements
- Bachelor's degree in Computer Science or a related field, or equivalent experience.
- Expertise in efficient models with a deep understanding of computational bottlenecks and acceleration methods.
- Proficiency training generative AI or LLM models with PyTorch and JAX.
- Strong communication and collaboration skills in fast-paced environments.
- Preferred: Ph.D. in GenAI, MLSys, or an equivalent background.
- Preferred: extensive research experience in GenAI, MLSys, or LLMs.
- Preferred: experience with image or video generation and editing, model compression, efficient architectures, efficient model design, or reinforcement-learning training methods such as RLHF, DPO, or GRPO.
Tech Stack
Categories
About ByteDance
ByteDance is a global incubator of platforms at the cutting edge of commerce, content, entertainment and enterprise services - over 2.5bn people interact with ByteDance products including TikTok. Creation is the core of ByteDance's purpose. Our products are built to help imaginations thrive. This is doubly true of the teams that make our innovations possible. Together, we inspire creativity and enrich life - a mission we aim towards achieving every day. At ByteDance, we create together and grow together. That's how we drive impact - for ourselves, our company, and the users we serve. We are committed to building a safe, healthy and positive online environment for all our users. We have over 110,000 employees based in more than 30 countries globally. Join us.