Navan Innovation & Technology Culture

What’s it like to work on the AI and machine learning team at your company?

Working on the AI team means architecting for extreme velocity. The environment is fast-paced and constantly shifting, driven by rapid prototyping through vibe coding, rigorous evals and single-turn LLM testing. My role is to ensure our technical foundation is flexible enough to support this pace. We routinely refactor, rebuild and ship in days instead of months — relying on adaptable design to turn that speed into a reliable engineering advantage.

How is your team applying emerging technology in practical, business-relevant ways?

At Navan, practical AI adoption means moving from theoretical breakthroughs to operational value very quickly. The architecture is designed to seamlessly integrate new models, techniques and design patterns the moment they emerge. And we leverage AI across the entire engineering and operational lifecycle — from automated code reviews and dev workflows to real-time system monitoring and automated support. Because the technical foundation is built to be modular and adaptive, new tech can be ingested at a speed that directly accelerates the business.

What should candidates know about the tools, collaboration or problem-solving involved in AI work at your company?

Candidates need to know that Navan is an intensely fast-paced company where things change very often and joining this team comes with exceptionally high expectations. Our tech stack is highly pragmatic; we leverage LangChain and all the major LLM providers, writing agents in both TypeScript and Python, alongside our own internal Navan Cognition platform. 

With the technology and priorities shifting so quickly, it’s impossible to keep track of everything manually. Instead, we rely on automated validation to maintain code quality, stepping into design meetings only when needed. We move with high autonomy and deploy using feature flags, giving us the safety net to ship fast and instantly disable a feature if a bug occurs. 

To thrive here, you have to be comfortable with constant evolution and be able to “think like the LLM” to diagnose prompt conflicts and model failures. We look for open-minded, zero-ego and data-driven engineers who can handle the pace. We move fast, but we never compromise on the final output — flawless, high-quality delivery is our absolute priority.

What new technologies or frameworks are helping your teams move faster and build smarter?

Claude Code is my best friend when it comes to AI coding. I also run Cursor on a self-hosted pool so it can handle tasks in the background while I’m away from my computer. On the infrastructure side, we rely on Braintrust for AI logs, monitoring and evals. I even have a Cursor automation set up to periodically pull Braintrust metrics, identify areas where our AI features could improve and refine the prompts or code accordingly. For us, the fastest and smartest work happens when multiple tools operate together in a flywheel.

How do you balance experimentation with reliability in your development process?

Reliability is what enables our experimentation and ability to move fast. We run extensive evals upfront to prove a concept works, roll it out behind feature flags and run continuous evals in production to make sure nothing drifts. We also always keep a human in the loop. Combining that with background automations that monitor metrics and refine prompts automatically gives the team total freedom to experiment without risking production.

What role does collaboration play in turning innovative ideas into products? 

Just like our AI features rely on feedback loops to get smarter, our product development process runs on the exact same model (and we’ve been doing it since before LLMs were a twinkle in our eyes). Since the early days of Navan, we’ve held open product requirements and design reviews where literally anyone in the company, from sales and customer success to engineering, accounting, finance and product, can jump in. Attendance is completely optional, yet dozens of people show up every time to voice their opinions and stress test ideas. Having those diverse perspectives in the room early catches blind spots before we write a single line of code, turning rough concepts into products our customers actually love.