Research Scientist
Bitdeer · Technology
- Work arrangement: remote in country
- Employment type: Full Time
- Seniority: senior
- Posted:
Job description
Position:
Research Scientist-Model Efficiency
Company:
Bitdeer
Location:
Singapore, SG / Austin, US
Employment type:
Full-Time
Short Summary:
Bitdeer AI Lab is seeking a Research Scientist to enhance model efficiency, making models cheaper and faster to serve without compromising quality.
Responsibilities:
- Implement and adapt published methods on models and hardware.
- Develop optimizations for model efficiency.
- Build evaluation discipline for performance claims.
Requirement:
- Bachelor's, Master's, or PhD in Computer Science, Electrical Engineering, or related field.
- Hands-on experience in LLM inference, model optimization, or ML systems.
- Strong programming ability in Python; familiarity with PyTorch, C++, CUDA, or Triton is a plus.
- Genuine depth in model efficiency areas (quantization, sparsity, etc.).
- Strong understanding of transformer internals.
- Experience in production serving or equivalent research depth preferred.
- Familiarity with inference engines (vLLM, SGLang, TensorRT-LLM) is preferred.
- Publications at top-tier venues or substantial open-source contributions are welcome.
- Deep enthusiasm for AI infrastructure and efficient inference.
Benefits:
- Culture valuing authenticity and diversity.
- Inclusive environment with open workspaces.
- Opportunities to network with industry pioneers.
- Direct contribution to the digital asset industry's future.
- Personal accountability, autonomy, and growth opportunities.
- Attractive welfare benefits and developmental opportunities.
Research Scientist-Model Efficiency
Company:
Bitdeer
Location:
Singapore, SG / Austin, US
Employment type:
Full-Time
Short Summary:
Bitdeer AI Lab is seeking a Research Scientist to enhance model efficiency, making models cheaper and faster to serve without compromising quality.
Responsibilities:
- Implement and adapt published methods on models and hardware.
- Develop optimizations for model efficiency.
- Build evaluation discipline for performance claims.
Requirement:
- Bachelor's, Master's, or PhD in Computer Science, Electrical Engineering, or related field.
- Hands-on experience in LLM inference, model optimization, or ML systems.
- Strong programming ability in Python; familiarity with PyTorch, C++, CUDA, or Triton is a plus.
- Genuine depth in model efficiency areas (quantization, sparsity, etc.).
- Strong understanding of transformer internals.
- Experience in production serving or equivalent research depth preferred.
- Familiarity with inference engines (vLLM, SGLang, TensorRT-LLM) is preferred.
- Publications at top-tier venues or substantial open-source contributions are welcome.
- Deep enthusiasm for AI infrastructure and efficient inference.
Benefits:
- Culture valuing authenticity and diversity.
- Inclusive environment with open workspaces.
- Opportunities to network with industry pioneers.
- Direct contribution to the digital asset industry's future.
- Personal accountability, autonomy, and growth opportunities.
- Attractive welfare benefits and developmental opportunities.
Skills
- performance_marketing
- cuda
- python
- pytorch
Languages
EN
Apply
Open this job in our interactive board to apply, save it, or sign up for matched alerts on similar roles.
View & apply