Research Scientist-Model Efficiency

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

About Bitdeer

Bitdeer is a world-leading technology company for Bitcoin mining and AI cloud. Bitdeer is committed to providing comprehensive Bitcoin mining solutions for its customers. Apart from designing industry-leading ASIC chips and manufacturing mining rigs, the Group handles complex processes involved in computing across the value chain. This includes equipment procurement, transport logistics, datacenter design and construction, equipment management, and network and facility operations. Bitdeer also offers advanced cloud capabilities to customers with a high demand for artificial intelligence.

Headquartered in Singapore, Bitdeer operates globally with a diversified 3 GW energy portfolio, and deploys Bitcoin mining and HPC datacenters in the United States, Bhutan, Norway, Canada, Malaysia, and Ethiopia.

About Bitdeer AI Lab

Bitdeer AI Lab is a frontier AI lab under Bitdeer, a global-leading computing power solutions provider. Guided by long-termism, we are committed to exploring the frontiers of artificial intelligence with the ambition, courage, and determination to build technologies that can truly change the world.

Our mission is to turn energy into intelligence that people can actually afford to use. Inference is where that happens: every product built on a model is bounded by what it costs to run, so the economics of serving decide what gets built at all. We work on this from the ground up, from the power and datacenters we own to the software that turns them into tokens — and we continue to invest in and expand the infrastructure behind it.

Responsibilities

This role makes models cheaper and faster to serve without giving up quality that matters. You are not limited to prescribing one technique — quantization, sparsity and pruning, speculative decoding and MTP, and serving-time attention and KV-cache methods are all in scope. You will implement and adapt published methods on our models and hardware, and develop your own optimizations where they fall short. You will also build the evaluation discipline that makes a claim like "lossless at 2× throughput" defensible.

Requirements

• Bachelor's, Master's, or 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 — and the ability to state honestly what a number does and does not prove

Preferred Qualifications

• Experience taking efficiency methods into production serving, or equivalent research depth


• Familiarity with inference engines such as vLLM, SGLang, or TensorRT-LLM and their efficiency features


• Publications at top-tier systems or ML venues, or substantial open-source contributions


• Deep enthusiasm for cutting-edge AI infrastructure and efficient inference, with a strong ownership mentality and solid engineering discipline

What You Will Experience Working With Us

• A culture that values authenticity and diversity of thoughts and backgrounds


• An inclusive and respectable environment with open workspaces and exciting start-up spirit


• Fast-growing company with the chance to network with industrial pioneers and enthusiasts


• Ability to contribute directly and make an impact on the future of the digital asset industry


• Involvement in new projects, developing processes and systems


• Personal accountability, autonomy, fast growth, and learning opportunities


• Attractive welfare benefits and developmental opportunities such as training and mentoring