Efficient GenAI Research Engineer: Distillation

ByteDance; San Jose (CA); On-site; USD 254,000 - 588,000; Full time

Job summary

ByteDance is seeking a Research Engineer/Scientist to design and implement efficient models for large-scale generative AI, with emphasis on distillation, compression, and deployment. You will work on model acceleration and hardware-aware inference within the Vision-Applied Research team in San Jose.

The role requires experience in quantization, diffusion/ autoregressive methods, and a strong background in PyTorch or JAX to optimize model performance and scalability for real-world applications.

Qualifications

• Bachelor's degree in CS or related field or equivalent experience.
• Expertise in efficient models with understanding of bottlenecks and acceleration methods.
• Experience training generative AI or LLM models using PyTorch or JAX.

Responsibilities

• Develop efficient algorithms and architectures for large-scale generative and multimodal models, using distillation and quantization to improve efficiency.
• Advance scalable generative modeling approaches, including diffusion and autoregressive models, with focus on acceleration and efficiency.

Skills

Efficient models

Model distillation

Quantization

Large-scale generation

Hardware acceleration

PyTorch

JAX

Education

Bachelor's degree in Computer Science or related field

Ph.D. in GenAI, MLSys or equivalent

Tools

PyTorch

JAX

Job description

ByteDance is seeking a Research Engineer/Scientist to design and implement efficient models for large-scale generative AI, with emphasis on distillation, compression, and deployment. You will work on model acceleration and hardware-aware inference within the Vision-Applied Research team in San Jose.

The role requires experience in quantization, diffusion/ autoregressive methods, and a strong background in PyTorch or JAX to optimize model performance and scalability for real-world applications.