Sanas
Staff+ Production Engineer
Palo Alto, CA · Staff+
Sponsorship not specifiedDetected 25 days ago
PythonRustDistributed SystemsAWSGCPAzureCloud PlatformsTerraformPrometheusGrafanaDatadogMachine LearningIncident ResponseRoadmappingSystems EngineeringCommunication
About the role
- This role involves architecting and delivering deployment infrastructure across public and corporate private clouds (AWS, Azure, and GCP).
- Standardize and orchestrate world-class on-call documentation, incident response processes, and post-mortem procedures.
Responsibilities
- Job Description Design and implement mission-critical, multi-region deployment infrastructure on AWS to ensure exceptional scalability and fault tolerance.
- Drive developer velocity by engineering and maintaining rapid, high-confidence development, testing, and staging deployment workflows.
- Establish and maintain a cohesive, state-of-the-art telemetry, monitoring, and alerting ecosystem to achieve deep operational observability and industry-leading system uptime.
- Our team combines deep expertise in model innovation and systems engineering with a design-minded product engineering culture to build and ship cutting-edge AI models and experiences - entirely in-house.
- Our innovation has been supported by the industry's leading investors, including Insight Partners, Google Ventures, Quadrille Capital, General Catalyst, Quiet Capital, and other influential investors.
- About the Role We are seeking a Production Engineer to take complete, end-to-end ownership of the infrastructure that builds, deploys, and operates our high-scale, real-time speech AI platform globally.
Requirements
- Possess strong "engineering taste" and the ability to define, champion, and enforce a high-quality bar for operational excellence and site reliability across the entire organization.
- Deep experience with GPU performance tuning, resource orchestration, and scaling for AI/ML workloads.
- Familiarity with the unique challenges of real-time, low-latency systems, particularly conversational speech or streaming services, aligning with Sanas's core voice pipelines.
Skills
- Proven mastery of infrastructure-as-code and containerization technologies, specifically Terraform and Docker.
Company info
- We are seeking a Production Engineer to take complete, end-to-end ownership of the infrastructure that builds, deploys, and operates our high-scale, real-time speech AI platform globally.
This listing is sourced directly from Sanas's careers page and normalized into a canonical job model.