Staff SRE: AI Gateway Platform, Scalable Infra

Kraken; Argentina; Remote; ARS 184,752,000 - 277,128,000; Full time

Job summary

Kraken is building the AI Gateway, a production-critical service powering internal LLM access. We seek a Senior SRE to own reliability, SLOs, on-call practices and incident response across Kraken's platform.

You will design resilient gateway architecture, implement multi-provider routing and observability, and mentor engineers to raise the team-wide operating standard while balancing cost and performance.

Qualifications

• Extensive experience in site reliability, infrastructure or platform engineering with ownership of high-traffic, production services.
• Strong hands-on skills with Kubernetes, major cloud providers and infrastructure as code.
• Solid grasp of SLOs, observability, incident management and prioritizing reliability work.

Responsibilities

• Own the reliability, availability and performance of the AI Gateway as a production-critical service used across Kraken.
• Design gateway resilience: multi-provider routing, failover, retries, rate limiting and graceful degradation.
• Set technical direction for gateway architecture, capacity planning and scaling as traffic grows and workloads increase.
• Build observability for LLM traffic: latency, errors, token usage and cost.
• Partner with Security, Finance and AI governance to enforce access controls, budgets and audit logging.
• Lead incident response and blameless post-incident reviews to drive reliability improvements.
• Automate operations: infrastructure as code, safe deployments and progressive rollouts.
• Mentor engineers and raise operating standards across Dev Platform.

Skills

Site reliability

Kubernetes

IaC

SLOs & monitoring

Rust / Python

API gateways

Consul & Vault

Auth & IAM

Model eval pipelines

Agent harnesses

Vector stores

Staff-level influence

Reliability vs cost

Tools

Kubebuilder

Controller-runtime

Ray

vLLM

Job description

Kraken is building the AI Gateway, a production-critical service powering internal LLM access. We seek a Senior SRE to own reliability, SLOs, on-call practices and incident response across Kraken's platform.

You will design resilient gateway architecture, implement multi-provider routing and observability, and mentor engineers to raise the team-wide operating standard while balancing cost and performance.