Staff Site Reliability Engineer (AI)

Location: Remote in Brazil, Argentina, Chile, Colombia, Mexico, or Peru

Company

hirify.global is a crypto platform operated by Payward, building globally accessible financial infrastructure and products for individual and institutional clients.

What you will do

• Own the reliability, availability, performance, SLOs, error budgets, and on-call practices for the company-wide AI Gateway.
• Design multi-provider routing, failover, retries, rate limiting, caching, and graceful degradation for LLM traffic.
• Set architecture, capacity planning, and scaling direction as gateway usage grows.
• Build observability for latency, errors, token usage, and cost by team and use case.
• Partner with Security, Finance, and AI governance stakeholders on access controls, budgets, audit logging, and data handling.
• Lead incident response and post-incident reviews, automate operations through infrastructure as code and progressive rollouts, and mentor engineers.

Requirements

• Extensive site reliability, infrastructure, or platform engineering experience owning high-traffic, business-critical production services.
• Hands-on experience with Kubernetes, a major cloud provider, and infrastructure as code such as Terraform.
• Strong command of SLOs, observability, and incident management, with sound judgment about reliability priorities.
• Proficiency in Rust or Python and ability to contribute to a production codebase.
• Experience with API gateways, reverse proxies, or traffic management, including load balancing, rate limiting, failover, and caching.
• Experience with Consul and Vault for service discovery, configuration, and secrets management.
• Working knowledge of OAuth 2.0/OIDC, JWT, mTLS, and API keys for multi-tenant internal platforms and APIs.
• Experience operating model evaluation pipelines and familiarity with coding agents, agent harnesses, sandboxed environments, agent memory systems, and vector, search, relational, or key-value databases.
• Staff-level influence: setting direction across teams, writing design documents, and balancing reliability, cost, and developer velocity.

Nice to have

• Experience operating LLM gateways or integrating LLM provider APIs at scale.
• Experience hosting models with vLLM and operating distributed inference or training workloads with Ray.
• Experience designing and maintaining Kubernetes controllers and operators, including CRDs, reconciliation loops, and safe upgrades.
• Experience with cost attribution, budgeting, or FinOps for usage-based services.
• Background in security-sensitive or regulated financial services or crypto environments.
• Contributions to open-source gateway, proxy, or observability projects.

Culture & Benefits

• Remote role limited to applicants in Brazil, Argentina, Chile, Colombia, Mexico, or Peru.
• Applications are accepted on an ongoing basis unless a specific deadline is stated.
• Applicants may redact age, date of birth, and educational attendance or graduation dates from resumes.
• Qualified applicants with criminal histories are considered consistently with the San Francisco Fair Chance Ordinance.
• Payward promotes merit-based, inclusive hiring and considers candidates who do not fully meet every listed requirement.

Hiring process

• Job-related skills or work-style assessments may be required and are considered alongside experience and interviews.