We are looking for exceptional talent to join us helping build the inference foundation for frontier AI models.

This role is centered on ML systems research for large-scale inference optimization. You will focus on improving and extending SGLang- and vLLM-based serving stacks, optimizing inference for both open-source LLMs and reasoning models as well as future in-house models developed by Bitdeer AI Lab. Your work will span GPU kernel-level optimization, high-performance inter-node communication, and end-to-end serving system design on real production clusters of hundreds to thousands of GPUs, helping define the next generation of efficient AI inference infrastructure.

• Strong interest in ML systems research for large-scale inference optimization on hundreds to thousands of GPUs.
• Hands‑on experience with or strong familiarity with SGLang and vLLM, especially for large‑scale mode...