Senior Machine Learning Engineer Voice Agents

You will own major parts of a realtime voice-agent library and ship voice-agent product capabilities. You will design APIs and streaming protocols, build GPU inference serving, improve reliability, support deployments, and create documentation and examples.

Responsibilities

• Own architecture, pipeline design, latency, and realtime-loop reliability for speech-to-speech
• Integrate ASR, TTS, and end-to-end speech models
• Review pull requests, triage issues, and cut releases
• Design developer APIs and streaming protocols
• Build realtime GPU inference serving with concurrency, autoscaling, and observability
• Perform load testing and define service-level objectives
• Write documentation, examples, and templates
• Support production deployments

Requirements

• Experience owning substantial architecture autonomously
• Experience building developer-facing AI or developer-tools infrastructure
• Open-source contributions to a Python library
• Experience with async Python and distributed systems
• Experience shipping realtime streaming, WebSockets, WebRTC, audio, video, or live inference
• Production experience with LLMs or multimodal models
• Clear written communication
• Interest in voice and conversational AI

Benefits

• Conference travel and preparation time
• Conference, training, and education reimbursement
• Flexible working hours
• Remote work options
• Health, dental, and vision benefits for employees and dependents
• Parental leave
• Flexible paid time off
• Workstation equipment
• Company equity