Site Reliability Engineer

10 hours ago

Ho Chi Minh City, VietnamMid Level / Senior

Responsibilities

Define and monitor SLOs and SLIs for availability, latency, time-to-first-audio, ASR/TTS quality, retrieval quality, call completion, and error budgets.
Participate in on-call rotations, respond to incidents, maintain runbooks, facilitate postmortems, and track reliability actions.
Build metrics, logs, traces, dashboards, and model-version-aware observability across ASR, LLM, TTS, RAG, and telephony systems.
Implement canary releases, progressive rollouts, regression detection, automated rollback, and load testing for voice endpoints.
Tune alerts to user impact, monitor capacity and model-provider quotas, and maintain dependency health checks and SLO-aligned dashboards.
Build or improve internal AI copilots for alert triage, log analysis, postmortem drafting, and runbook generation.

3–5 years of experience running production systems in SRE or strong DevOps roles.
Experience carrying a pager, responding to incidents, writing postmortems, and defining and monitoring SLOs and SLIs.
Experience with observability tools such as Prometheus, Grafana, OpenTelemetry, or Datadog.
Extensive Kubernetes experience, including networking, rollout deployment, and graceful shutdown.
Experience with CI/CD, rollback, progressive delivery, infrastructure as code, and a major cloud provider such as AWS, GCP, or Azure.
Ability to write production tooling in Python, Go, or Bash.
Daily use of AI/LLM tools such as Claude, ChatGPT, Cursor, or Copilot, with the ability to describe specific time savings.
Nice to have: experience with inference servers such as Triton or LLM gateways such as vLLM.
Nice to have: experience building internal tooling with LLMs and awareness of container scanning, secret management, dependency hygiene, and SBOMs.
Vietnamese–English bilingual working ability is a plus.

Competitive compensation package with a 13th-month salary and performance bonuses.
Comprehensive health care coverage for the employee and dependents.
Generous annual and sick leave policies with flexible work hours.
Central District 1 office location near a future metro station.
Onsite lunch with vegetarian options, Grab for work allowance, and fully equipped workstations.
Team-building activities, sponsored sports clubs, and weekly Thursday happy hours.
Unlimited free coffee, tea, snacks, and fruit.
Opportunity to work with senior and staff SRE mentors and contribute to social-impact credit access initiatives.
Onsite work arrangement indicated by the central office location and onsite lunch offering.

201-500 employees