Staff SRE Engineer - Voice Core Platform
Core
Own the reliability, performance, and operational architecture of a real-time conversational AI voice platform, ensuring low latency and high availability for orchestration of voice calls.
Role type
Staff Site Reliability Engineer (Voice Core Platform)
Builds
Real-time voice orchestration pipelines integrating VAD, STT, LLM agents, and TTS with ServiceNow APIs.
Domain
AI/ML infrastructure, Real-time Voice Systems, Cloud Infrastructure
Deliverable
production ML models
Required skills
SRE/DevOps at scale, Real-time voice systems (VoIP/SIP/WebRTC), AI agentic systems orchestration, LLM production deployment, Kubernetes, Cloud infrastructure (AWS/Azure/GCP), Infrastructure as Code (Terraform), Observability (OpenTelemetry/Prometheus/Grafana/Datadog), Python/Go/Java
Preferred skills
Inference serving (vLLM/Triton/GPU scheduling), ServiceNow platform experience
Responsibilities
Define and drive SLIs/SLOs for availability and latency, Instrument end-to-end tracing and lead latency reduction architecture, Design autoscaling and capacity plans for stateful real-time connections, Lead load/soak/breakpoint testing and capacity modeling, Build resilience for LLM/STT/TTS dependencies (failover/fallbacks), Own Kubernetes architecture and CI/CD, Lead incident response and mentor engineers
