AI Engineer, Workbench
$216k - $240k • San Francisco, California, United States
Posted 16d ago
About the job
Brex is seeking an AI Engineer to join their Finance Agents team and build the Agent Workbench. This role involves creating a conversational surface where finance professionals can interact with AI agents through various documents and tools to understand financial activity, investigate findings, and steer agent actions. The initial focus will be on evolving the workbench into an extensible platform supporting multiple agent experiences, owning the extension model, integration protocols, and application architecture. You will collaborate with cross-functional teams to build across application layers, establish an agentic design system, and iterate with customers on features like policy editing, reporting, and data exploration.
Responsibilities
- Design and build a reusable agent workbench platform supporting multiple agent personas and enabling team integration.
- Design and implement extension models, integration protocols, and application architecture for agent capabilities and user interactions.
- Build and ship customer-facing workflows combining conversation with documents, charts, spreadsheets, and interactive artifacts.
- Partner with engineering, Product, and Design to translate user needs into cohesive experiences, balancing usability, extensibility, and reliability.
- Own features from design through production, gathering customer feedback and improving agent understanding, configuration, and steering.
Requirements
- 5+ years of software development experience delivering customer-facing applications.
- Experience building or contributing to a production-grade agent, agent harness, workbench, or agentic product.
- Experience in application architecture and integration design, translating interaction needs into extensible interfaces and clear component boundaries.
- Deep familiarity with agent clients like Claude, ChatGPT, and OpenCode through sustained use.
- Strong product judgment and ownership in ambiguous environments, working effectively across teams and ensuring production quality.
Benefits
- Hybrid work environment
- Up to four weeks per year of fully remote work