AI Inference Engineer: Model Optimization and Efficiency

BITDEER AI PTE. LTD.; Singapore; On-site; SGD 120,000 - 200,000; Full time

Job summary

Bitdeer AI Lab in Singapore is looking for a talented AI inference engineer to make large language models cheaper and faster to serve while preserving quality. You will implement and adapt optimization techniques and build robust evaluation pipelines.

We value hands‑on experience in LLM inference, model optimization, and ML systems, with strong Python and PyTorch skills; knowledge of C++/CUDA is a plus. You will collaborate across hardware, software, and data teams to push frontier AI

Qualifications

• Hands-on experience in LLM inference, model optimization, or ML systems.
• Strong programming ability in Python and familiarity with PyTorch; C++, CUDA, or Triton is a plus.
• Understanding of transformer internals and where accuracy loss shows up in model behavior.
• Experience taking efficiency methods into production serving or equivalent research depth.

Responsibilities

• This role makes models cheaper and faster to serve without sacrificing essential quality.
• You will implement and adapt published optimization methods on our models and hardware.
• You will build evaluation pipelines to defend performance claims with solid metrics.

Skills

LLM inference

Model optimization

ML systems

Python

PyTorch

C++/CUDA knowledge

Education

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

Tools

C++

CUDA

Triton

vLLM

TensorRT-LLM

Job description

Bitdeer AI Lab in Singapore is looking for a talented AI inference engineer to make large language models cheaper and faster to serve while preserving quality. You will implement and adapt optimization techniques and build robust evaluation pipelines.

We value hands‑on experience in LLM inference, model optimization, and ML systems, with strong Python and PyTorch skills; knowledge of C++/CUDA is a plus. You will collaborate across hardware, software, and data teams to push frontier AI