Model Efficiency Research Scientist

Unchain Data; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

Bitdeer AI Lab is seeking a research-focused engineer to make models cheaper and faster to serve while maintaining quality. You will implement optimization techniques and build robust evaluation pipelines for scalable AI workloads.

You will work with Python, PyTorch, and potentially C++/CUDA, exploring quantization, pruning, and advanced serving-time methods to improve throughput and efficiency.

Qualifications

• Hands-on experience in LLM inference, model optimization, or ML systems.
• Proficient in Python and PyTorch; C++, CUDA, or Triton is a plus.
• Deep implementation-level depth in at least one area of model efficiency.
• Strong understanding of transformer internals and accuracy impact.

Responsibilities

• Make models cheaper and faster to serve without compromising quality.
• Implement and adapt published methods on our models and hardware; develop optimizations.
• Build evaluation discipline to support defensible performance claims.

Skills

Python

PyTorch

C++

CUDA

Triton

LLM inference

Model optimization

Transformer internals

Evaluation metrics

Quantization

Education

Bachelor's/Master's/PhD in CS or EE

Tools

vLLM

SGLang

TensorRT-LLM

Job description

Bitdeer AI Lab is seeking a research-focused engineer to make models cheaper and faster to serve while maintaining quality. You will implement optimization techniques and build robust evaluation pipelines for scalable AI workloads.

You will work with Python, PyTorch, and potentially C++/CUDA, exploring quantization, pruning, and advanced serving-time methods to improve throughput and efficiency.