Research Scientist – Model Efficiency Internship

About the role

We are looking for a Research Scientist Intern focused on model efficiency within Bitdeer AI Lab. You will work on making AI models cheaper and faster to serve while preserving quality, contributing to real‑world projects that impact our inference infrastructure.

Key responsibilities

• Implement and adapt state‑of‑the‑art techniques such as quantization, sparsity, pruning, speculative decoding, and serving‑time attention on our models and hardware.
• Develop original optimizations when existing methods fall short.
• Build rigorous evaluation pipelines to validate claims like “lossless at 2× throughput”.
• Own a well‑defined 3–6 month project and present results to the team.

Required profile

• Undergraduate, Master’s or PhD candidate in Computer Science, Electrical Engineering, Mathematics or a related field.
• Available full‑time for 3–6 months.
• Strong programming ability in Python and hands‑on experience with PyTorch.
• Coursework, self‑study or research experience in model efficiency (quantization, sparsity, pruning, speculative decoding, serving‑time attention, KV‑cache).

Required skills

• Python programming
• PyTorch framework