Not specified (additional research may be needed to determine if the position is onsite, hybrid, or remote).
Proficient in c/c++ programming
Strong algorithms and data structures knowledge
Understanding of deep learning principles
ByteDance is seeking a Software Engineer specializing in Inference to join their Machine Learning Systems team in Singapore. The role involves developing and optimizing large-scale machine learning inference frameworks, particularly focusing on GPU performance
Job Summary
The role involves developing and optimizing LLM inference frameworks for large-scale heterogeneous systems.
Candidates will focus on GPU and CUDA performance optimization to create industry-leading high-performance engines.
The team offers a global collaborative environment with members from the US, China, and Singapore working towards unified project directions.
Matching Summary
Match Score: 85
ByteDance is seeking a Software Engineer specializing in Inference to join their Machine Learning Systems team in Singapore. The role involves developing and optimizing large-scale machine learning inference frameworks, particularly focusing on GPU performance.
Skills & Requirements
Must-have
Proficient in C/C++ programming
Strong algorithms and data structures knowledge
Understanding of deep learning principles
Familiarity with PyTorch framework
Nice-to-have
GPU high-performance computing optimization
Experience with TensorRT-LLM or VLLM
Knowledge of LLM model acceleration
Parallel computing and memory access optimization
Key Requirements
Bachelor's degree in computer science or related field