Model Efficiency Research Scientist — Inference Optimization

Bitdeer Technologies Group; Austin (TX); On-site; USD 120,000 - 230,000; Full time

Benefits offered by this job

Training & mentoring

Open workspaces

Job summary

Bitdeer Technologies Group seeks an experienced machine learning engineer to optimize LLM inference and ML systems. You will implement and adapt efficiency methods, drive model performance, and push toward cheaper, faster serving without quality loss.

The role emphasizes hands-on deep learning engineering, with strong Python and PyTorch skills, and familiarity with C++/CUDA optional. This position is based in Austin, TX, on-site with a fast-growing AI infrastructure focus.

Qualifications

• Hands-on experience in LLM inference, model optimization, or ML systems.
• Strong programming ability in Python and deep familiarity with PyTorch.
• Experience delivering efficiency methods to production serving.

Responsibilities

• Make models cheaper and faster to serve without sacrificing quality.
• Implement quantization, sparsity and pruning, speculative decoding and MTP, or serving-time attention and KV-cache methods.
• Build evaluation discipline to defend throughput claims.

Skills

Python

PyTorch

C++

CUDA

LLM inference

Model optimization

Education

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

Tools

vLLM

SGLang

TensorRT-LLM

Job description

Bitdeer Technologies Group seeks an experienced machine learning engineer to optimize LLM inference and ML systems. You will implement and adapt efficiency methods, drive model performance, and push toward cheaper, faster serving without quality loss.

The role emphasizes hands-on deep learning engineering, with strong Python and PyTorch skills, and familiarity with C++/CUDA optional. This position is based in Austin, TX, on-site with a fast-growing AI infrastructure focus.