Tech Stack

Description

You will design and build the real-time streaming infrastructure that powers voice conversations with Claude, focusing on low-latency serving systems, APIs, and observability. You'll work at the intersection of real-time media, low-latency inference, and distributed systems to make voice interactions fast, reliable, and scalable.

Requirements

• 6+ years of experience building distributed systems, real-time infrastructure, or platform services at scale
• Shipped production systems with latency measured in tens of milliseconds
• Comfortable working across the stack from transport protocols to APIs
• Results-oriented with bias toward flexibility and impact
• Experience with real-time media protocols (WebRTC, RTP, gRPC streaming, WebSockets)

Responsibilities

• Design and build real-time streaming infrastructure for voice conversations with Claude
• Build low-latency serving systems for speech models, optimizing time-to-first-audio
• Develop public and internal APIs for voice capabilities across platforms
• Own audio transport layer: codecs, jitter buffers, adaptive bitrate, packet loss recovery
• Build observability and quality-measurement systems for voice