ML Systems Engineer – Large-Scale Inference on GPUs

Bitdeer AI Lab in Singapore invites applications for a role focused on ML systems research for large-scale inference across multi-GPU clusters. You will improve SGLang- and vLLM-based serving stacks and optimize inference for open-source LLMs and future in-house models.

Collaborate with research teams to fine-tune latency, throughput, and GPU efficiency, contributing to cutting-edge AI infrastructure in a fast-growing environment.