ML Infrastructure Engineer — Model Hub

About the Role

Join Hugging Face as an ML Infrastructure Engineer to build the systems that serve millions of model downloads and inference requests every day.

What You'll Build

• Scalable model serving infrastructure (Inference Endpoints)
• CI/CD pipelines for model validation and deployment
• Monitoring and observability for ML workloads
• Developer tooling for the Hugging Face Hub

About Us

We're a fully remote, globally distributed team that believes in open-source AI. You'll work on infrastructure used by millions of ML practitioners worldwide.

• 3+ years infrastructure/DevOps/MLOps experience
• Strong Kubernetes and Docker expertise
• Experience with model serving (TGI, vLLM, Triton)
• Proficiency in Python and Go/Rust is a plus

• Fully remote globally
• Competitive salary + equity
• Open-source contribution time (20% of work time)
• Annual hardware budget