ML Engineer — Inference Optimization

About the Role

Hugging Face is hiring an ML Engineer to optimize inference performance across our model hub. You will work on model optimization techniques, develop efficient serving infrastructure, and build tools that make running ML models faster and cheaper for the community.

Requirements

• 4+ years of experience in ML engineering or systems optimization
• Deep understanding of model inference and optimization techniques
• Proficiency in Python, C++, and CUDA
• Experience with model quantization, distillation, or pruning
• Familiarity with inference frameworks (ONNX Runtime, TensorRT, vLLM)

Nice to Have

• Contributions to Hugging Face Optimum or TGI
• Experience with hardware-specific optimizations (ARM, Apple Silicon)
• Background in compiler optimization
• Experience with serverless inference platforms

Benefits

Skills

Related Jobs