Staff Site Reliability Engineer - Dev Platform
Core
Own the reliability, availability, and performance of the AI Gateway, a company-wide LLM gateway providing self-service access to leading models with visibility, cost controls, and routing.
Role type
Staff Site Reliability Engineer (Dev Platform)
Builds
AI Gateway (LLM routing, failover, observability, access controls)
Domain
Financial services / AI Infrastructure
Deliverable
production ML models
Required skills
Kubernetes, Infrastructure as Code (Terraform), SLOs/Observability/Incident Management, Rust or Python, API Gateways/Reverse Proxies, Consul, Vault, OAuth 2.0/OIDC/JWT/mTLS, Model Evaluations, Coding Agents, Vector Stores/Relational Databases
Preferred skills
LLM Gateway operations, vLLM/Ray, Kubernetes Controllers/Operators, FinOps, Security-sensitive environments, Open-source contributions
Technologies
Kubernetes, Terraform, Rust, Python, Anthropic, OpenAI, Google, Consul, Vault, vLLM, Ray, OpenHands, Claude Code
Responsibilities
Own reliability/SLOs/error budgets for AI Gateway, design resilience (routing/failover/retries), set technical direction for architecture/scaling, build observability for LLM traffic, partner on security/governance/access controls, lead incident response, automate operations via IaC, mentor engineers
Seniority
Staff, hands-on IC with team influence
