Staff SRE Engineer - Voice Core Platform
ServiceNow2 days ago
Hyderābād, IndiaStaff+
Responsibilities
- Define and drive SLIs and SLOs for availability, perceived latency, and call quality.
- Instrument end-to-end tracing and lead architectural work to reduce latency.
- Design autoscaling and capacity plans for stateful real-time connections using WebSocket, WebRTC, and SIP/RTP.
- Lead load, soak, and breakpoint testing and develop capacity models from the results.
- Build failover, fallback, rate-limit handling, and graceful degradation for LLM, STT, and TTS dependencies.
- Own Kubernetes architecture, infrastructure-as-code, and safe progressive delivery.
- Lead incident response and postmortems while mentoring engineers across the team.
Requirements
- 8+ years of experience in SRE, DevOps, production engineering, or software engineering on production systems at scale.
- At least 1 year of experience building or operating real-time voice systems, including VoIP, SIP/RTP, WebRTC, or STT/TTS integration.
- At least 2 years of experience building or operating AI agentic systems and orchestration pipelines.
- At least 1 year of experience deploying and operating LLMs in production, including model serving, inference optimization, or provider integration and failover.
- Strong expertise in Kubernetes, cloud infrastructure such as AWS, Azure, or GCP, and Terraform or similar tools.
- Hands-on observability experience with OpenTelemetry, Prometheus, Grafana, Datadog, or similar tools.
- Proficiency in Python, Go, or Java.
- Experience with inference serving such as vLLM, Triton, or GPU scheduling is preferred.
- Familiarity with the ServiceNow platform or enterprise SaaS backends is preferred.
- Experience leveraging or critically evaluating AI in work processes, decision-making, or problem-solving is required.
Benefits
- Flexible work persona within a distributed work environment.
- Regular employee position in the APAC region.
- ServiceNow provides reasonable accommodation support for candidates who need assistance during the application process.
Tech Stack
Categories
DevOpsSite Reliability
About ServiceNow
ServiceNow builds a cloud platform for enterprise digital workflows, covering IT service management, customer service, HR service delivery, security operations, and operations management, plus tools for custom app development. It sells subscription SaaS to large organizations and public-sector agencies to automate processes and connect data across systems. Founded in 2004 and headquartered in Santa Clara, California, ServiceNow is a public company listed on the NYSE under the ticker NOW.