SlipstreamJobs tracks this role from the company's public career site. Apply directly on the employer's site.
Brex is an intelligent finance platform serving tens of thousands of companies globally with corporate cards, banking, spend management, and AI-native automation. The Operational AI team builds the AI systems and internal platforms that make Brex's operations AI-native, from customer onboarding and KYC automation to AI-powered support.
As a Senior Software Engineer on the Operational AI team, you will own the technical direction and roadmap of Brex's Agents Platform—an internal system for building, evaluating, and running AI agents in production. This platform already powers critical automations in customer onboarding and AI tools for sales and customer success teams. You will evolve it from simple workflows into sophisticated agents that take action, making it the default way Brex ships AI into its operations.
Key responsibilities include:
- Owning the technical direction and roadmap of Agents Platform, partnering with leadership and internal teams to prioritize what the platform should build next
- Designing and building new platform capabilities: tool calling, multi-step agent loops, multi-turn conversational execution, and secure access to internal Brex data and services
- Evolving the evaluation and quality system—from datasets and labeling to run comparison and regression testing—so teams can measure and improve non-deterministic systems with production rigor
- Strengthening reliability, security, and observability in business-critical flows like customer onboarding, including durable async/batch execution, authorization, cost attribution, and incident response
- Partnering with engineering, operations, and go-to-market teams to launch and scale high-impact agents, translating requirements into clear platform capabilities
- Driving adoption by making the platform easy to build on through clear contracts, documentation, and AI-native developer workflows
- Mentoring engineers through design reviews, code reviews, and pairing; helping grow the team's technical bench
The role is based in São Paulo with a hybrid model requiring a minimum of three coordinated days in office per week (Monday, Wednesday, Thursday), plus up to four weeks per year of fully remote work.
REQUIREMENTS:
- 5+ years of professional software engineering experience with a track record of designing, building, and operating reliable production backend systems
- Deep, hands-on experience using AI coding tools (Claude Code, Cursor, etc.) in daily work, with judgment to ship faster without lowering quality
- Hands-on experience shipping LLM-powered systems to production beyond prototypes: orchestrating model calls, enforcing structured outputs, evaluating quality over time
- Experience with distributed and asynchronous systems and reliability concerns (retries, idempotency, backpressure, observability)
- Platform mindset: experience building shared infrastructure, developer tooling, or paved roads adopted by other engineers; care for developer experience and secure-by-default design
- High ownership and operational excellence, including on-call, incident response, and end-to-end system ownership
- Strong written and verbal communication; ability to prioritize across internal customers including non-engineers; English proficiency required (interviews conducted in English)
BONUS POINTS:
- Experience building eval frameworks, LLM gateways, or agent platforms used by other teams
- Experience with Temporal or other durable workflow engines
- Experience with service and agent authorization (RBAC, scoped credentials, agents acting on behalf of users)
- Production experience with tool use, MCP, retrieval, or agentic loops
- Background in ML engineering, MLOps, or data infrastructure
- Experience in fintech or regulated environments where auditability and model governance matter
