Senior Software Engineer (Voice Backend)

📋 Description

• Design real-time voice backend with low-latency streaming (WebRTC, SIP, RTP) and ASR→LLM→TTS.
• Manage session/conversation state for thousands of concurrent calls with reliable handoff.
• Build high-throughput, scalable services for routing speech and language models in real time.
• Integrate and operate streaming ASR and TTS engines with VAD and graceful degradation.
• Engineer reliability: failover, retries, backpressure, and latency observability.
• Design APIs and Pub-Sub interfaces to connect voice runtime to Workato.

🎯 Requirements

• Bachelor’s in CS or related field, or equivalent experience.
• 5+ years building backend services and distributed systems (Python preferred, Go/Java).
• Hands-on with real-time, low-latency systems (WebRTC/SIP/RTP) or streaming (WebSocket/gRPC).
• Experience integrating streaming ASR/TTS engines as production services (protocols, codecs, VAD/endpointing, barge-in).
• Experience serving ML/LLM models in production focusing on tail latency, concurrency, throughput.
• Understanding of LLMs/ASR/TTS behavior in production: latency, streaming, failure modes.

🎁 Benefits

• Flexible, trust-oriented culture that empowers ownership.
• Vibrant, dynamic work environment with a range of benefits.