Research Engineer – Model Efficiency (Intern)

About the role

Join Bitdeer AI Lab as a Research Engineer Intern focused on model efficiency. You will work on making AI models cheaper and faster to serve while preserving quality, using techniques such as quantization, sparsity, pruning, speculative decoding, and serving‑time attention.

Key responsibilities

• Implement and adapt published model‑efficiency methods on Bitdeer’s models and hardware.
• Develop custom 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 related field.
• Available full‑time for 3–6 months.
• Strong programming ability in Python and hands‑on experience with PyTorch.
• Experience or coursework in model efficiency (quantization, sparsity, pruning, speculative decoding, serving‑time attention, KV‑cache).
• Solid understanding of transformer internals and rigorous evaluation habits.

Required skills

• Python
• PyTorch

What we offer

• Inclusive, diverse culture with an open workspace and start‑up spirit.
• Opportunity to impact the digital asset and AI industry directly.
• Access to mentorship, training, and fast‑growth learning experiences.
• Attractive welfare benefits and developmental opportunities.