Start Your Search Here

Job Search

BYTEDANCE PTE. LTD.

Singapore / Global

Backend Engineer - GPU-Optimized Large-Model Inference

Job Description

ByteDance PTE. LTD. is seeking an experienced engineer to advance the large model inference engine, optimize GPU performance, and develop distributed parallel solutions across tensor, pipeline, sequence, and MoE parallelism.

The role involves adapting to diverse hardware architectures and benchmarking against leading frameworks. You will work within the AML team on high-impact AI infrastructure for ads ranking, search ranking, live & e-commerce platforms, contributing to scalable, low-latency

#J-18808-Ljbffr

Apply Now

Similar Opportunities

View all jobs