Senior Software Engineer, Operational AI
Salary not listed • São Paulo, São Paulo, Brazil • Full-time
Posted 29d ago
About the job
Brex is seeking a Senior Software Engineer to join the Operational AI team, focusing on building and evolving Brex's internal platform for creating, evaluating, and running AI agents in production. This platform is crucial for automating critical internal operations, such as customer onboarding and providing AI tools for sales and customer success teams. The role involves owning the technical direction of the platform, enhancing its capabilities to support complex agent interactions and secure data access, and strengthening its evaluation and reliability systems. The goal is to make this platform the standard for deploying AI within Brex's operations, directly impacting the company's ability to onboard, serve, and grow its customer base.
Responsibilities
- Own the technical direction and roadmap for the Agents Platform, collaborating with leadership and user teams.
- Design and build new platform features, including tool calling, multi-step agent workflows, and secure data/service access.
- Enhance the evaluation and quality system for non-deterministic AI systems with production-grade rigor.
- Improve the reliability, security, and observability of systems in critical business flows like customer onboarding.
- Partner with cross-functional teams to launch and scale high-impact AI agents.
- Drive platform adoption by improving developer experience through clear contracts, documentation, and workflows.
- Mentor team members and other engineers through code reviews, design reviews, and pairing.
Requirements
- 5+ years of professional software engineering experience, with a focus on reliable production backend systems.
- Deep, hands-on experience with AI coding tools (e.g., Claude Code, Cursor) for daily work.
- Proven experience shipping LLM-powered systems to production, including orchestration, output enforcement, and quality evaluation.
- Experience with distributed and asynchronous systems, including reliability concerns like retries and idempotency.
- A platform mindset, with experience building shared infrastructure or developer tooling.
- High ownership and operational excellence, including on-call and incident response.
- Strong written and verbal communication skills, with the ability to prioritize across diverse internal customers.
- English proficiency is required for interviews.
Benefits
- Up to four weeks per year of fully remote work.