Research Engineer – Model Efficiency

About the role

Bitdeer AI Lab is seeking a Research Engineer to make AI models cheaper and faster to serve without sacrificing quality. You will work on cutting‑edge efficiency techniques and build rigorous evaluation practices.

Key responsibilities

• Implement and adapt published model‑efficiency methods (quantization, sparsity, pruning, speculative decoding, MTP, serving‑time attention, KV‑cache, etc.) on Bitdeer’s models and hardware.
• Develop original optimizations when existing methods fall short and establish defensible evaluation metrics such as “lossless at 2× throughput”.

Required profile

• Bachelor's, Master's or PhD in Computer Science, Electrical Engineering or related field with hands‑on experience in LLM inference, model optimization or ML systems.
• Strong programming ability in Python and deep familiarity with PyTorch; experience with C++, CUDA or Triton is a plus.

Required skills

• Python
• PyTorch
• C++ (optional)
• CUDA (optional)
• Triton (optional)
• Knowledge of transformer internals and model‑efficiency techniques (quantization, sparsity, pruning, speculative decoding, MTP, KV‑cache).

What we offer

• A culture that values authenticity, diversity and an inclusive environment.
• Opportunities to work on fast‑growing, cutting‑edge AI infrastructure projects.
• Personal accountability, autonomy, rapid growth and learning opportunities.
• Attractive welfare benefits and developmental programs such as training and mentoring.