Software Engineer, Forward Deployed Agent Builder

Why join us

Brex is the intelligent finance platform that enables companies to spend smarter and move faster in more than 200 markets. By combining global corporate cards and banking with intuitive spend management, bill pay, and travel software, Brex enables founders and finance teams to accelerate operations, gain real-time visibility, and control spend effortlessly. Brex’s AI-native automation and world-class service eliminate manual expense and accounting tasks for customers so they can focus on what matters most.

Engineering at Brex

Engineering at Brex is about building systems that scale with speed and intention. Our teams span Software, Data, Security, and IT, and operate with high autonomy and deep collaboration. We tackle hard technical problems, own our outcomes, and push for excellence at every level — from architecture to deployment. It’s an environment where engineering is a craft, and builders become leaders.

What you’ll do

We're building AI agents to automate and augment internal functions at Brex, and we're looking for a hands-on builder to help us do it. You'll embed with teams across the company to understand how they actually work, then design, build, and ship agents that deliver real outcomes. You'll work on top of existing models and frameworks, wiring together tools, MCPs, and internal systems into agentic workflows. This is a technical role where you'll spend most of your time building, shipping, and iterating alongside the people whose work you're automating.

Where you’ll work

This role will be based in our San Francisco office. We are a hybrid environment that combines the energy and connections of being in the office with the benefits and flexibility of working from home. We currently require a minimum of three coordinated days in the office per week, Monday, Wednesday, and Thursday. As a perk, we also have up to four weeks per year of fully remote work!

Responsibilities:

• Embed with partner teams to deeply understand workflows, including shadowing and learning different job functions.
• Scope, design, and deploy agents that take over real workflows across internal orgs.
• Integrate agents with internal systems, APIs, and data sources.
• Define evaluation frameworks, success metrics, and feedback loops to measure and improve agent performance.
• Build shared tooling and contribute to playbooks that accelerate deployments, while owning reliability, adoption, and business impact.

Requirements:

• 4+ years in engineering, technical product/program management, applied AI, or a similar technical role, with a track record of shipping AI/automation systems to production.
• Hands-on experience building with LLMs, agent frameworks, and tool-use patterns (e.g., MCP, function calling, RAG) across the full stack (data, APIs, orchestration, product).
• Experience designing and optimizing SQL and/or NoSQL databases, including data modeling, query performance tuning, and schema design.
• Strong ability to decompose human workflows into scalable, agentic systems, grounded in a deep curiosity for how people work.
• High ownership and cross-functional influence, with the ability to quickly build trust across teams and seniority levels.

Bonus points

• Experience automating back-office functions rather than just customer-facing AI features.
• Experience with OpenClaw, Hermes, or other general-purpose agent harnesses.

Compensation:

The expected salary range for this role is $152,000 - $240,000. However, the starting base pay will depend on a number of factors including the candidate’s location, skills, experience, market demands, and internal pay parity. Depending on the position offered, equity and other forms of compensation may be provided as part of a total compensation package.