Hugging Face

Machine Learning Engineer

• Own architecture for substantial parts of the speech-to-speech open-source library, including pipeline design, latency budget, and realtime-loop reliability
• Integrate new ASR, TTS, and end-to-end speech models while maintaining clean abstractions
• Review community pull requests, triage issues, cut releases, and grow project contributors
• Design the hf-voice developer API and streaming protocol, including session lifecycle, WebSockets/WebRTC transport, authentication, error semantics, and versioning
• Build realtime GPU inference serving with concurrency, autoscaling, observability, and cost-per-session optimization
• Collaborate with Hub and inference teams to simplify voice-agent integration into products and demos
• Take hf-voice from demo to production through load testing, SLOs, and graceful degradation
• Write documentation, examples, and templates for developers
• Support existing deployments, beginning with the Reachy Mini fleet
• Publicly discuss the work through blog posts, demos, or conference talks

Senior Machine Learning Engineer, Voice Agents