Research Engineer, Efficient ML

Hugging Face is looking for a Research Engineer focused on efficient ML to work on model compression, quantization, and optimization techniques. You'll contribute to our open-source libraries (PEFT, bitsandbytes, optimum) and help make state-of-the-art models accessible to everyone — including those without access to expensive hardware.

Your work will directly impact millions of developers who rely on Hugging Face to run models efficiently.

• Strong ML engineering background
• Experience with model quantization, pruning, or distillation
• Proficiency in Python and PyTorch
• Understanding of hardware architectures (GPU, CPU, edge devices)
• Experience with ONNX or TensorRT is a plus
• Open-source contribution experience preferred

• Fully remote
• Competitive salary
• Equity
• Health benefits
• Open-source impact