Staff SRE Engineer - Voice Core Platform

Own reliability, performance, and operational architecture of a real-time conversational AI voice platform focusing on latency and availability.

Define and drive SLIs/SLOs for availability, latency, and call quality; lead architectural improvements and operational testing (load, soak, breakpoint).

Lead Kubernetes infrastructure, autoscaling, capacity planning, incident response, and mentor engineering teams across multiple dependencies (LLM, STT, TTS).

8+ years experience in SRE, DevOps, production engineering, or software engineering on production systems at scale.

1+ year experience building or operating real-time voice systems (VoIP, SIP/RTP, WebRTC, STT/TTS integration).

2+ years experience building or operating AI agentic systems and orchestration pipelines with multi-step LLM workflows.

Strong expertise in Kubernetes, cloud infrastructure (AWS/Azure/GCP), Terraform or similar, plus observability tools (OpenTelemetry, Prometheus, Grafana, Datadog).

Deep experience in end-to-end operational responsibility for high-scale, latency-sensitive voice platforms integrating AI components.

Proven ability to architect and optimize real-time pipelines including LLM serving and multi-step AI orchestration under reliability SLIs/SLOs.

Advanced cloud native engineering skills combined with infrastructure as code and scalable automated deployment expertise.