Research Scientist: Efficient AI Inference

Bitdeer (NASDAQ: BTDR); Austin (TX); On-site; USD 140,000 - 220,000; Full time

Job summary

Bitdeer AI Lab is seeking an ML/LLM inference engineer to optimize models for cost and speed. You will implement quantization, sparsity, and other efficiency techniques, and build robust evaluation to support performance claims.

Ideal candidates have strong Python/PyTorch skills, experience with C++, CUDA or Triton, and a track record in bringing efficiency methods to production or research depth. Austin-based role with growth in AI cloud infrastructure.

Qualifications

• 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.
• 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.
• Understanding transformer internals and where accuracy loss shows up in model behavior.
• Rigorous evaluation practices with task-level metrics, honest baselines, and clear statements about what numbers prove.
• Experience taking efficiency methods into production serving or equivalent research depth.
• Familiarity with inference engines like vLLM, SGLang, or TensorRT-LLM and their efficiency features.
• Publications at top-tier venues or substantial opensource contributions are welcome.
• Strong enthusiasm for cutting-edge AI infrastructure and ownership mentality.

Responsibilities

• Make models cheaper and faster to serve without sacrificing important quality.
• Implement and adapt published optimization methods on our models and hardware.
• Build an evaluation discipline to defend claims like 2× throughput.
• Bring production-ready efficiency methods into serving pipelines.

Skills

Python

PyTorch

C++

CUDA

Triton

Model efficiency

Transformer internals

Evaluation practice

Production experience

Inference engines

Publications/Open source

Ownership mindset

Education

Bachelor's/Master's/PhD in CS or Electrical Engineering or related field

Tools

vLLM

SGLang

TensorRT-LLM

Job description

Bitdeer AI Lab is seeking an ML/LLM inference engineer to optimize models for cost and speed. You will implement quantization, sparsity, and other efficiency techniques, and build robust evaluation to support performance claims.

Ideal candidates have strong Python/PyTorch skills, experience with C++, CUDA or Triton, and a track record in bringing efficiency methods to production or research depth. Austin-based role with growth in AI cloud infrastructure.