Staff SRE: AI Gateway Reliability Architect

Kraken; México; On-site; MXN 1,200,000 - 1,800,000; Full time

Job summary

Kraken’s Dev Platform team seeks a Senior Site Reliability Engineer to own the AI Gateway’s reliability, availability and performance in production. You will design resilience with multi-provider routing, failover, retries, rate limiting and graceful degradation while guiding architecture for growing LLM workloads.

You will build observability for LLM traffic including latency, errors and cost, partner with Security and AI governance, and lead incident response plus blameless post-incident

Qualifications

• Extensive experience in site reliability and owning high-traffic services.
• Strong hands-on with Kubernetes, cloud providers and IaC (Terraform).
• Familiar with SLOs, observability and incident management.

Responsibilities

• Own the reliability, availability and performance of the AI Gateway in production.
• Design gateway resilience including routing, failover, retries and rate limiting.
• Set technical direction for gateway architecture, capacity planning and scaling.
• Build observability for LLM traffic: latency, errors, token usage and cost.
• Lead incident response and post-incident reviews to drive improvements.

Skills

Site reliability

Kubernetes

Terraform

SLOs

Observability

Incident mgmt

Rust or Python

API gateways

Consul Vault

Auth protocols

Model evals

Agent harnesses

Vector stores

Leadership

Tools

Kubernetes controllers

Kubernetes operators

Job description

Kraken’s Dev Platform team seeks a Senior Site Reliability Engineer to own the AI Gateway’s reliability, availability and performance in production. You will design resilience with multi-provider routing, failover, retries, rate limiting and graceful degradation while guiding architecture for growing LLM workloads.

You will build observability for LLM traffic including latency, errors and cost, partner with Security and AI governance, and lead incident response plus blameless post-incident