Staff Site Reliability Engineer – Dev Platform

This is a fully remote position, open to applicants in Brazil, +5 more countries.

📋 Description

• Take ownership of the reliability, availability, and performance of the AI Gateway, which is a critical service across the company.

• Establish service level objectives (SLOs), error budgets, and on-call procedures.

• Design routing across multiple providers, along with failover, retries, rate limiting, and graceful degradation mechanisms.

• Define the technical vision for the gateway architecture, including capacity planning and scaling strategies.

• Create observability metrics for LLM latency, error rates, token consumption, and costs categorized by team and use case.

• Collaborate with Security, Finance, and AI governance stakeholders on access management, budget oversight, audit logging, and data processing.

• Lead the incident response process and facilitate blameless post-incident evaluations.

• Streamline operations through the use of infrastructure as code, secure deployments, and progressive rollout strategies.

• Mentor fellow engineers and elevate operational standards within the Dev Platform team.

⛳️ Requirements

• Significant experience in site reliability, infrastructure, or platform engineering roles.

• Proven history of managing high-traffic, mission-critical production services.

• Extensive hands-on expertise with Kubernetes, a leading cloud service provider, and infrastructure as code tools like Terraform.

• Strong understanding of SLOs, observability practices, and incident management protocols.

• Proficient in Rust or Python, with the capability to contribute to a production service codebase.

• Experience with API gateways, reverse proxies, or traffic management techniques, including load balancing, rate limiting, failover, and caching.

• Familiarity with Consul and Vault for service discovery, configuration management, and secrets handling.

• Working knowledge of OAuth 2.0/OIDC, JWT, mTLS, and API keys applicable to multi-tenant platforms and APIs.

• Experience in model evaluation pipelines for models, prompts, and agents.

• Acquainted with coding agents and agent harnesses such as OpenHands or Claude Code, including sandboxed execution.

• Knowledgeable in agent memory systems and various database types, including vector, search, relational, and key-value stores.

• Ability to exert staff-level influence, provide technical direction, and create design documentation.

• Sound judgment in balancing reliability, cost, and development speed.

• Nice to have: Experience with LLM gateway/provider APIs, vLLM, Ray, Kubernetes controllers/operators, FinOps, and working in security-sensitive or regulated environments.

🏝️ Benefits

• Flexible remote work options.

• Commitment to equal opportunity employment.

• Consistent application of job-related skills or work-style assessments.

• Chance to engage with global financial infrastructure and open finance products.