Sanas
Staff+ Production Engineer
Palo Alto, CA · On-site · Staff · Full-time · Posted Apr 13, 2026
- Experience
- 5+ years; no alternatives stated.
About the job
Owns the infrastructure and operational systems for deploying and running Sanas’s real-time speech AI platform across public and corporate private clouds.
What you'll do
- Design and operate scalable, fault-tolerant, multi-region deployment infrastructure and workflows across cloud environments.
- Build and maintain telemetry, monitoring, alerting, on-call, incident response, and post-mortem systems.
- Develop self-service tools and documentation that help engineering teams manage and scale services.
What they ask for
- 5+ years of hands-on Platform/Production engineering experience operating high-availability production environments on AWS.
- Expertise with Terraform and Docker.
- Experience with cloud monitoring and observability systems such as Datadog, NewRelic, or Prometheus/Grafana.
- Ability to build and maintain internal tooling and automation using Python or Rust.
Nice to have
- Deployment and operational experience with Azure or GCP.
- GPU performance tuning and orchestration for AI/ML workloads; real-time low-latency systems experience is also a bonus.
Tools
AWS, Azure, GCP, Terraform, Docker, Datadog, NewRelic, Prometheus/Grafana
AI focus
The role operates infrastructure for a real-time speech AI platform; GPU tuning and scaling for AI/ML workloads are preferred bonus experience.
Model-written summary · the original posting is authoritative