Senior Software Engineer, Operational AI
About this role
The Operational AI team at Brex builds the internal platforms and AI systems that automate company operations, ranging from customer onboarding and KYC to AI-powered support. This group operates as a compact unit with a broad scope, directly impacting how efficiently the business serves its customer base.
As a Senior Software Engineer, you will lead the technical direction of Agents Platform, the internal system used to build, evaluate, and run production AI agents. Your day-to-day work involves evolving this platform from simple workflows into active agents while partnering with various departments to expand adoption and reliability.
This role suits an engineer with a strong background in distributed backend systems and production LLM deployment who enjoys building shared infrastructure and developer tooling. Candidates should thrive in a hybrid setup based in the São Paulo office and possess strong communication skills for collaborating across engineering and go-to-market teams.
What you will do
- Own the technical roadmap and direction for Agents Platform in partnership with Operational AI leadership.
- Design and implement core platform capabilities like multi-step agent loops, tool calling, and conversational execution.
- Improve evaluation and quality systems through datasets, labeling, and regression testing for non-deterministic setups.
- Enhance the reliability, security, and observability of systems handling business-critical flows like customer onboarding.
- Collaborate with engineering, operations, and go-to-market teams to launch and scale high-impact AI agents.
- Drive internal adoption by establishing clear contracts, documentation, and developer workflows.
- Mentor engineers across the organization through design reviews, code reviews, and pairing sessions.
What you need
- Bring 5 or more years of professional software engineering experience focused on designing and operating reliable backend systems.
- Demonstrate hands-on daily use of AI coding tools such as Cursor or Claude Code to ship software efficiently.
- Show direct experience shipping LLM-powered applications to production beyond simple prototypes, including orchestrating model calls and structured outputs.
- Possess solid knowledge of distributed and asynchronous systems, covering reliability patterns like retries, backpressure, and idempotency.
- Exhibit a platform mindset through previous work building shared infrastructure, developer tooling, or internal paved roads.
- Maintain high ownership and operational excellence through practices like on-call rotations and end-to-end system stewardship.
- Demonstrate strong written and verbal English communication skills for cross-functional collaboration and interviews.
Nice to have
- Experience building eval frameworks, LLM gateways, or agent platforms used by other teams.
- Experience with Temporal or another durable workflow engine.
- Experience with service and agent authorization, such as RBAC, scoped credentials, or agents acting on behalf of users.
- Production experience with tool use, MCP, retrieval, or agentic loops.
- A background in ML engineering, MLOps, or data infrastructure, as well as fintech or regulated environments.
Skills and tech stack
Questions candidates ask
Where is this role located and what is the remote policy?
This role is based in the São Paulo office in a hybrid environment. Brex requires a minimum of three coordinated days in the office per week on Monday, Wednesday, and Thursday, alongside up to four weeks per year of fully remote work.
What will I be working on primarily?
You will focus on Agents Platform, Brex's internal platform for building, evaluating, and running AI agents in production. Your work will involve evolving its technical direction from simple workflows into agents that take action.
What qualifications are required for this position?
Applicants need at least five years of professional software engineering experience with production backend systems. You also need hands-on experience shipping LLM-powered systems to production and using AI coding tools in daily work.
How can I ensure I am communicating with a legitimate recruiter?
Brex recruiters will only reach out via LinkedIn or through an email address with a brex.com domain. Any outreach claiming to be from Brex via other sources should be ignored.