Staff Site Reliability Engineer - Dev Platform

The role

You will own the reliability of the Developer Platform AI, including the AI Gateway, agent runtime, and connections to internal tools. You will design resilience across model providers and build observability for LLM traffic, latency, and cost. The role involves setting technical direction and automating operations with infrastructure as code.

What you will do

• Own the reliability of the AI Gateway, agent runtime, and connections to internal tools
• Set SLOs and own error budgets
• Design resilience across model providers including routing, failover, retries, rate limiting and graceful degradation
• Build observability for latency, errors, token usage and cost
• Treat capacity and cost as one problem
• Work with Security, Finance and AI governance to implement 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 raise the operating standard across the team
• Set technical direction for how the platform runs

Required qualifications

• Extensive experience in site reliability, infrastructure or platform engineering
• Track record of owning high-traffic, business-critical services in production
• Deep hands-on experience with Kubernetes
• Experience with a major cloud provider
• Experience with infrastructure as code such as Terraform
• Strong command of SLOs, observability and incident management
• Proficiency in Rust or Python
• Comfort reading and changing a production service's code
• Experience with API gateways, reverse proxies or traffic management
• Experience operating multi-tenant internal platforms including authentication, authorization and per-tenant cost controls
• Staff-level influence to set direction across teams and write design documents

Nice to have

• Experience operating LLM gateways or integrating LLM provider APIs at scale
• Experience serving models yourself, including vLLM or Ray
• Experience building Kubernetes controllers or operators with controller-runtime or kubebuilder
• Experience with Consul and Vault
• Experience with model evaluation pipelines
• Familiarity with coding agents and agent harnesses
• Experience with cost attribution, budgeting or FinOps for usage-based services
• Background in security-sensitive or regulated environments such as financial services or crypto
• Contributions to open-source gateway, proxy or observability projects

Before you apply

• We may ask candidates to complete job-related skills or work-style assessments

About the company

Payward is the parent company behind Kraken, NinjaTrader, Breakout, xStocks, Payward Services and CF Benchmarks. Kraken is a crypto platform trusted by over 10 million individuals and institutions.