Research Engineer: Efficient LLM Inference

Bitdeer Technologies Group; Singapore; On-site; SGD 120,000 - 200,000; Full time

Job summary

Bitdeer Technologies Group, via its Bitdeer AI Lab, seeks a skilled professional to optimize LLM inference and ML systems for scalable, cost-efficient deployment. You will work on model optimization—quantization, sparsity, pruning—and matching hardware capabilities to achieve high throughput without quality loss.

You will collaborate across teams to push efficient AI infrastructure, with a focus on transformer internals, rigorous evaluation, and production-ready solutions.

Qualifications

• Bachelor's/Master's/PhD in Computer Science, Electrical Engineering, or a 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.
• Genuine implementation-level depth in at least one area of model efficiency, such as quantization, sparsity and pruning, speculative decoding and MTP, or serving-time attention and KV-cache methods.
• Strong understanding of transformer internals and where accuracy loss actually shows up in model behaviour.
• Rigorous evaluation practice — task-level metrics, controlled comparisons, honest baselines.
• Experience taking efficiency methods into production serving, or equivalent research depth, is highly preferred.
• Familiarity with inference engines such as 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.

Responsibilities

• Make models cheaper and faster to serve without sacrificing important quality. Implement and adapt published methods on our models and hardware, and develop optimizations where they fall short.
• Build the evaluation discipline to defend claims like 'lossless at 2× throughput.'

Skills

Python

PyTorch

LLM inference

Model optimization

C++

Education

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

Tools

vLLM

SGLang

TensorRT-LLM

CUDA

Triton

Job description

Bitdeer Technologies Group, via its Bitdeer AI Lab, seeks a skilled professional to optimize LLM inference and ML systems for scalable, cost-efficient deployment. You will work on model optimization—quantization, sparsity, pruning—and matching hardware capabilities to achieve high throughput without quality loss.

You will collaborate across teams to push efficient AI infrastructure, with a focus on transformer internals, rigorous evaluation, and production-ready solutions.