Staff Site Reliability Engineer Dev Platform
Posted Updated
Description
You will own the AI Gateway's reliability, availability, performance, resilience, capacity, observability, and incident response. You will automate operations, implement security and cost controls, guide technical direction, and mentor engineers across the developer platform.
Responsibilities
- Own AI Gateway reliability, availability, performance, SLOs, and on-call practices
- Design resilience through routing, failover, retries, rate limiting, and graceful degradation
- Set technical direction for architecture, capacity planning, and scaling
- Build observability for latency, errors, token usage, and cost
- Implement platform access controls, budgets, audit logging, and data handling
- Lead incident response and post-incident reviews
- Automate operations with infrastructure as code and progressive rollouts
- Mentor engineers and raise operating standards
Requirements
- Site reliability engineering
- Infrastructure engineering
- Platform engineering
- Kubernetes
- Cloud computing
- Infrastructure as code
- Terraform
- SLO
- Observability
- Incident management
- Rust
- Python
- API gateway
- Reverse proxy
- Load balancing
- Rate limiting
- Failover
- Caching
- Consul
- Vault
- OAuth
- OIDC
- JWT
- mTLS
- API key
- Model evaluation
- Agent
- Vector database
- Search
- Relational database
- Key-value database
