Salary not listed
Staff Site Reliability Engineer - Dev Platform
DevOpsRemote — Brazil, Peru, Colombia, Argentina, Mexico, Chile
Published on 2026-10-28
These details were extracted automatically from the original listing. They may not be complete or fully up to date — it's worth checking the original job post.
About this role
Own the reliability, performance, and resilience of Kraken’s company-wide AI Gateway, a governed platform for accessing LLM providers. Set technical direction as usage scales, improve observability and operational practices, and help teams use AI services securely and efficiently.
About the company
Kraken is a leading cryptocurrency exchange that provides a platform for buying, selling, and trading a diverse range of digital assets. The company focuses on compliance, security, and innovative financial solutions to serve both individual and institutional clients.
The team
Dev Platform team, responsible for the internal platform engineers use to build, ship, and run software.
Stack
KubernetesTerraformRustPythonConsulVaultOAuth 2.0OIDC
What you'll do
- Own AI Gateway reliability, availability, performance, SLOs, error budgets, and on-call practices.
- Design provider routing, failover, retries, rate limiting, and graceful degradation.
- Set gateway architecture, capacity-planning, and scaling direction.
- Build observability for latency, errors, token usage, and cost by team and use case.
- Partner with Security, Finance, and AI governance on access controls, budgets, audit logging, and data handling.
- Lead incident response and blameless post-incident reviews.
- Automate operations with infrastructure as code, safe deployments, and progressive rollouts.
- Mentor engineers and improve operating standards across Dev Platform.
What we're looking for
- Extensive SRE, infrastructure, or platform engineering experience owning business-critical production services.
- Hands-on experience with Kubernetes, a major cloud provider, and infrastructure as code such as Terraform.
- Strong expertise in SLOs, observability, and incident management.
- Proficiency in Rust or Python and ability to contribute to production codebases.
- Experience with API gateways, reverse proxies, or traffic management.
- Experience with Consul and Vault.
- Knowledge of authentication and authorization for multi-tenant services, including OAuth 2.0/OIDC, JWT, mTLS, or API keys.
- Staff-level technical leadership, including setting direction and writing design documents.
Nice to have
- Experience operating LLM gateways or integrating LLM provider APIs at scale.
- Experience serving models with vLLM or running distributed inference and training with Ray.
- Experience building Kubernetes controllers and operators.
- Experience with cost attribution, budgeting, or FinOps.
- Background in financial services, crypto, or other security-sensitive environments.
- Open-source contributions to gateway, proxy, or observability projects.