AI Architect (Voice AI)

📋 Description

• Own the technical architecture and delivery of the voice copilot from PoC to production
• Improve latency, accuracy, and concurrency metrics in production
• Protect the team from scope creep and manage expectations with client
• Transfer knowledge to client and Neurons Lab engineers continuously

🎯 Requirements

• Real-time voice pipelines: streaming STT, low-latency LLM inference
• LLM engineering: prompt design, structured extraction, guardrails, evals
• Observability: Langfuse, dashboards for latency, accuracy, cost
• AWS: Bedrock, SES, serverless patterns
• Full-stack: Python; TS/Chrome-extension knowledge
• Clear spoken/written English for US executives