Senior ML Systems Scientist — High-Performance Inference

ByteDance; San Jose (CA); On-site; USD 212,800 - 387,600; Full time

Benefits offered by this job

Medical insurance

Dental insurance

Vision insurance

401(k) match

Parental leave

Disability insurance

Wellbeing benefits

Paid holidays

Job summary

ByteDance Technology in San Jose is seeking a Senior Research Scientist to lead machine learning system development. You will help build and optimize large-scale distributed ML training and inference infrastructure, integrating GPU/NPU/RDMA and storage to run complex models reliably.

Join a global team and contribute to cutting-edge LLM/AI system work while enhancing performance analysis, distributed systems, and decision-making processes across multiple regions.

Qualifications

• Bachelor's degree or above in computer/electronics/automation/software, etc.
• Proficient in C/C++, algorithms and data structures; familiar with Python.
• Understand basic principles of deep learning and PyTorch frameworks.

Responsibilities

• Develop and optimize LLM inference framework.
• Improve GPU/CUDA performance to create a high-performance LLM inference engine.

Skills

C/C++

Python

Algorithms & data structures

Deep learning basics

PyTorch

Education

Bachelor's degree

Tools

TensorRT-LLM

ORCA

VLLM

Job description

ByteDance Technology in San Jose is seeking a Senior Research Scientist to lead machine learning system development. You will help build and optimize large-scale distributed ML training and inference infrastructure, integrating GPU/NPU/RDMA and storage to run complex models reliably.

Join a global team and contribute to cutting-edge LLM/AI system work while enhancing performance analysis, distributed systems, and decision-making processes across multiple regions.