Staff Site Reliability Engineer - Dev Platform

BUILDING THE FUTURE OF OPEN FINANCE Payward - the parent company behind Kraken, NinjaTrader, Breakout, xStocks, Payward Services and CF Benchmarks - has spent the last 15 years building one of the most modern and globally accessible financial infrastructure platforms in the industry, built to advance an open, global financial system. THE TEAM Founded in 2011, Kraken is one of the world's longest-standing crypto platforms, trusted by over 10 million individuals and institutions across the globe. It offers spot trading, margin, futures, staking, and OTC services, with products built for both individual investors and institutional clients. Kraken's engineers build a lot of software. Developer Platform AI builds the AI systems they use to do it: agents that write and review code, simple access to the best models in the tools they already use, and the infrastructure that connects AI to our internal systems. This is a small team with a lot of reach. The tools you ship will change how engineers across Kraken work every day, and you'll see that happen directly. The work spans agent platforms, code review, LLM routing and cost controls, MCP integrations with tools like Slack, Jira and GitLab, and the security and observability that make all of it safe to run. If you want to work on applied AI with real users from day one, this is that job.   THE OPPORTUNITY - LLM traffic doesn't behave like normal API traffic. Requests are long-running, streaming and expensive. One prompt can cost a few cents or a few dollars. One team's burst can burn another team's budget. Providers change their rate limits, failure modes and pricing without warning. Running this well is a problem few companies have solved, and it's the job. - Own the reliability of the platform engineers depend on: the AI Gateway, the agent runtime and the connections to internal tools. Set the SLOs, own the error budgets and decide what happens when they're spent. - Design resilience across model providers: routing, failover, retries, rate limiting and graceful degradation when a provider is slow, throttling or down. - Make LLM traffic legible. Build observability that shows latency, errors, token usage and cost by team, model and use case, so engineers can see what their workloads cost and where they're spending their time waiting. - Treat capacity and cost as one problem. Routing decisions affect both latency and spend, and you'll own the tradeoff directly. - Work with Security, Finance and AI governance to put access controls, budgets, audit logging and data handling into the platform, not into a spreadsheet next to it. - Lead incident response and blameless post-incident reviews. Turn what breaks into fixes that stay fixed. - Automate operations with infrastructure as code, safe deployments and progressive rollouts, so the platform gets more reliable as it grows rather than more fragile. - Mentor engineers and raise the operating standard across the team. This is a Staff role. You'll set the technical direction for how the platform runs, not just keep it running. The platform is small enough that your decisions shape it directly, and used broadly enough that they affect every engineering team at Kraken. SKILLS YOU SHOULD HODL - Extensive experience in site reliability, infrastructure or platform engineering, with a track record of owning high-traffic, business-critical services in production - Deep hands-on experience with Kubernetes, a major cloud provider and infrastructure as code such as Terraform - Strong command of SLOs, observability and incident management, and the judgment to know which reliability work actually matters - Proficiency in Rust or Python, and comfort reading and changing a production service's code - Experience with API gateways, reverse proxies or traffic management: load balancing, rate limiting, failover and caching - Experience operating multi-tenant internal platforms, including authentication, authorization and per-tenant cost controls - Staff-level influence: you set direction across teams, write clear design documents and bring other engineers with you NICE TO HAVES - Experience operating LLM gateways or integrating LLM provider APIs at scale: streaming, token-based rate limiting, model routing and caching - Experience serving models yourself, including vLLM or Ray: GPU scheduling, batching, autoscaling and cost per token - Experience building Kubernetes controllers or operators with controller-runtime or kubebuilder - Experience with Consul and Vault for service discovery, configuration and secrets - Experience with model evaluation pipelines for catching quality regressions before and after rollout - Familiarity with coding agents and agent harnesses, and running them safely in sandboxed environments - 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 Unless a specific application deadline is stated in the job posting, applications are accepted on an ongoing basis. Please note, applicants are permitted to redact or remove information on their resume that identifies age, date of birth, or dates of attendance at or graduation from an educational institution. We consider qualified applicants with criminal histories for employment on our team, assessing candidates in a manner consistent with the requirements of the San Francisco Fair Chance Ordinance. OUR COMMITMENT Payward is powered by people from around the world and we celebrate the diverse talents, backgrounds, contributions, and unique perspectives that everyone brings to the table. We hire based on merit, seeking out people with the right abilities, knowledge, and skills for the job. We encourage you to apply for roles where you don't fully meet the listed requirements, especially if you're passionate or knowledgeable about crypto. We may ask candidates to complete job-related skills or work-style assessments as part of our hiring process. These assessments evaluate competencies relevant to the role and are applied consistently across candidates for similar positions. Results are considered alongside experience and interviews, and are not the sole basis for any employment decision. As an equal opportunity employer, we don't tolerate discrimination or harassment of any kind, whether based on race, ethnicity, age, gender identity, citizenship, religion, sexual orientation, disability, pregnancy, veteran status, or any other protected characteristic as outlined by federal, state, or local laws. Stay connected Follow us on Twitter https://twitter.com/krakenfx Learn on the Kraken Blog https://blog.kraken.com/#:~:text=Enter%20your%20email%20address Connect on LinkedIn https://www.linkedin.com/company/kraken-exchange/ Candidate Privacy Notice https://www.kraken.com/legal/candidate-privacy-notice