AI Model Optimization Engineer — Speech & Audio

ByteDance; San Jose (CA); Sur place; USD 128 000 - 256 000; Plein temps

Résumé du poste

ByteDance in San Jose, CA is seeking an AI Model Optimization Engineer to push the limits of model efficiency and deployment at scale. You will design algorithms for quantization, pruning, and distillation, and collaborate with research and engineering to bring optimized models into production.

Success requires strong Python and C++ skills, a solid understanding of GPU architectures, and experience with deep learning frameworks.

Qualifications

• Bachelor's/Master's degree in computer engineering or related field.
• Strong coding skills in Python and C++ (proficient).

Responsabilités

• Develop and implement algorithms for model optimization, including quantization, pruning, knowledge distillation, and efficient architectures.
• Build and maintain performance benchmarking frameworks for large-scale training and inference.
• Optimize training and inference pipelines on GPUs and across distributed systems.
• Collaborate with ML researchers to transition optimized models into production.
• Stay current with the latest research in model efficiency, compilers, and systems.

Connaissances

Python

C++

Formation

Bachelor's or Master's degree in computer engineering or related field

Description du poste

ByteDance in San Jose, CA is seeking an AI Model Optimization Engineer to push the limits of model efficiency and deployment at scale. You will design algorithms for quantization, pruning, and distillation, and collaborate with research and engineering to bring optimized models into production.

Success requires strong Python and C++ skills, a solid understanding of GPU architectures, and experience with deep learning frameworks.