Senior Software Engineer - Dev Platform

Accountabilities: Build and extend the AI Gateway by integrating new models and providers, implementing routing policies, and developing budget controls, rate limits, and usage and cost reporting. Design and maintain clean, scalable APIs, SDKs, and self-service tools that help engineering teams onboard quickly and use AI services safely. Support the migration of existing LLM workloads to the gateway while minimizing disruption to internal users and production systems. Implement access controls, API key management, authentication mechanisms, and audit logging in collaboration with security stakeholders. Develop observability capabilities that provide teams with visibility into latency, errors, token consumption, and costs across their workloads. Own features throughout the software development lifecycle, from technical design and implementation to deployment, monitoring, and ongoing improvements. Collaborate with site reliability engineering teams to maintain service availability, performance, resilience, and operational quality. Provide clear documentation, troubleshooting support, and technical guidance to internal users, incorporating their feedback into platform improvements. Contribute to code reviews, design discussions, technical documentation, and engineering standards across the developer platform team. Requirements Demonstrated experience as a backend or platform software engineer building, deploying, and operating APIs and distributed services in production environments. Strong proficiency in at least one backend programming language, such as Rust, Python, or TypeScript, with a commitment to writing clean, maintainable, well-tested code. Practical understanding of LLM APIs, including authentication, streaming responses, token accounting, rate limits, and provider failures. Experience with observability practices, CI/CD pipelines, and containerized applications, along with working knowledge of Kubernetes and at least one major cloud provider. Ability to design well-documented APIs and developer tools for internal customers, balancing technical considerations with usability and user feedback. Strong problem-solving skills, clear written and verbal communication, and the ability to take ownership of projects from conception through production. A collaborative mindset and the ability to work effectively across engineering, security, and operations teams in a distributed environment. Nice to have: Experience with API gateways, reverse proxies, or traffic management systems. Experience building LLM-powered applications or infrastructure, including model routing, caching, evaluation, and cost-control mechanisms. Familiarity with authentication and authorization standards and practices, such as OAuth, OpenID Connect (OIDC), and role-based access control (RBAC). Contributions to open-source infrastructure, backend systems, or developer-platform projects. Benefits Remote work flexibility: Work remotely from Brazil as part of a globally distributed team. Meaningful technical impact: Help shape the infrastructure that enables engineering teams to build and deploy AI-powered solutions. Modern engineering environment: Work with LLM providers, distributed services, cloud infrastructure, and developer-platform technologies. End-to-end ownership: Drive technical initiatives from design through implementation, deployment, and continuous improvement. Cross-functional collaboration: Partner with engineering, security, and reliability specialists to build secure and dependable systems. Professional growth: Strengthen your expertise in backend engineering, AI infrastructure, API design, and platform development. Inclusive culture: Join an environment that values diverse backgrounds, perspectives, skills, and contributions.