Research Scientist / Engineer – Inference Systems

About the role

Join Bitdeer AI Lab to lead cutting‑edge research and implementation of inference systems that power large language models at scale. You will work closely with the AI Cloud platform team to turn research ideas into production‑ready serving stacks.

Key responsibilities

• Explore frontier research on inference architectures, tiered caching, and disaggregated serving for agentic workloads.
• Design, implement, and ship system‑level improvements that meet real‑fleet performance and cost targets.
• Collaborate with the production team to integrate research outcomes into the live serving stack.

Required profile

• Master's or PhD in Computer Science, Electrical Engineering or related field (exceptional bachelor's candidates considered).
• Proven track record of both research publications or open‑source contributions and delivering working code.

Required skills

• Strong Python and C++ programming.
• Deep understanding of LLM inference and serving systems, with hands‑on experience in at least one engine such as vLLM or SGLang.
• Ability to define measurements, analyze results honestly, and optimise based on data.

What we offer

• Inclusive, diverse culture with an open‑space work environment.
• Fast‑growing company providing networking with industry pioneers.
• Opportunities for direct impact on the digital asset and AI infrastructure sectors.
• Training, mentoring, and attractive welfare benefits.