Ciridae AI
Member of Technical Staff, Platform
San Francisco +1 · On-site · Staff · Full-time · Posted May 6, 2026
- Location
- San Francisco
New York
About the job
Build and maintain the platform infrastructure that runs production AI deployments across multiple customer environments.
What you'll do
- Develop multi-tenant infrastructure, reliability, and cost controls for non-deterministic production systems.
- Build evaluation and observability systems for AI deployments.
- Create internal tooling that applies operational learnings to future deployments.
What they ask for
- Deep systems engineering experience with distributed systems, APIs, databases, and cloud infrastructure.
- Expert Python.
- Experience with Terraform, GCP, containers, and multi-tenant production systems.
Nice to have
- Go or TypeScript.
- Experience with LLM infrastructure such as model routing, evaluations, and cost and latency controls.
Tools
Python, Go, TypeScript, Terraform, GCP
AI focus
Production AI infrastructure, including model routing, evaluations, and cost and latency controls.
Model-written summary · the original posting is authoritative