Your browser does not support javascript! Please enable it, otherwise web will not work for you.

Research Engineer-Model Efficiency

Home > Python programming jobs

Research Engineer-Model Efficiency in Others new

  • BitDeer Technologies Group
  • Full time
  • Email
  • Singapore, Singapore

Responsibilities

  • Implement and adapt published model-efficiency methods for Bitdeer’s models and hardware.
  • Develop new optimizations for efficient LLM serving when existing techniques are insufficient.
  • Improve model serving cost and speed while preserving important quality.
  • Build rigorous evaluations using task-level metrics, controlled comparisons, and honest baselines.
  • Assess techniques including quantization, sparsity and pruning, speculative decoding, MTP, serving-time attention, and KV-cache methods.

Requirements

  • Bachelor’s, Master’s, or PhD in Computer Science, Electrical Engineering, or a related field.
  • Hands-on experience with LLM inference, model optimization, or ML systems.
  • Strong programming ability in Python and deep familiarity with PyTorch.
  • Implementation-level depth in at least one model-efficiency area, such as quantization, sparsity and pruning, speculative decoding and MTP, or serving-time attention and KV-cache methods.
  • Strong understanding of transformer internals and how accuracy loss affects model behavior.
  • Rigorous evaluation practice involving task-level metrics, controlled comparisons, and defensible baselines.
  • Experience with C++, CUDA, or Triton is a plus.
  • Production experience with efficiency methods or equivalent research depth is highly preferred.
  • Familiarity with vLLM, SGLang, or TensorRT-LLM and their efficiency features is highly preferred.
  • Publications at top-tier systems or ML venues or substantial open-source contributions are welcome.
  • Enthusiasm for AI infrastructure and efficient inference, ownership, and solid engineering discipline.

Benefits

  • Inclusive and respectful work environment with an open workspace and startup culture.
  • Opportunity to contribute directly to new projects and the future of the digital asset industry.
  • Networking opportunities with industry pioneers and enthusiasts.
  • Personal accountability, autonomy, fast growth, and learning opportunities.
  • Welfare benefits and development opportunities including training and mentoring.

BitDeer Technologies Group

Bitdeer Technologies Group (NASDAQ: BTDR) builds and operates Bitcoin‑mining infrastructure and AI/HPC cloud services for miners and enterprise compute customers. The Singapore‑headquartered public company, founded in 2021, designs ASIC chips and manufactures mining rigs, and runs data centers ac...

Similar positions

Founding ML Research Engineer

  • Clera
  • Full time
  • USA
  • 10/15/2026
  • Salary: $200k - $300k/yr
  • San Francisco, CA

Research Engineer

  • Lila Sciences
  • Full time
  • USA
  • 10/15/2026
  • Salary: $148k - $240k/yr
  • Cambridge, MA

AI Research Engineer

  • Tether.io
  • Full time
  • Remote
  • 10/14/2026
  • Worldwide

Research Engineer-Model Efficiency

  • BitDeer Technologies Group
  • Full time
  • Others
  • 10/14/2026
  • Singapore, Singapore

Offensive Security RL Researcher

  • Idler
  • Full time
  • USA
  • 10/13/2026
  • Salary: $200k - $500k/yr
  • San Francisco, CA