Backend Engineer for AI-Powered Expense Platform

Navan; Berlin (NH); Presencial; USD 74.000 - 108.000; Jornada completa

Descripción de la vacante

Navan is expanding Expense Engineering in Berlin and London to own the full expense lifecycle from receipts to GL. You will work on end-to-end expense product areas including international spend, tax receipts, policy, and audit, with AI-powered features already in the product.

You will design and ship backend services and web features, own APIs, and extend LLM-backed agents, with a focus on accuracy, latency, and safety across multi-entity setups.

Formación

• 1–3 years of software engineering experience.
• Strong CS fundamentals and backend experience in Java/Spring Boot, TypeScript/Node.js or Python.
• Java preferred but not mandatory if you have strong transferable backend skills.
• Experience with APIs, relational databases and cloud platforms.
• Exposure to AI tools or projects involving LLMs, chatbots, RAG, document processing or AI-assisted development.
• Interest in financial or workflow-heavy products such as payments, expenses, accounting or tax.
• Good communication, willingness to learn and understanding of testing, debugging and production-quality engineering.
• Based in Berlin or London, or willing to relocate.

Responsabilidades

• Design and ship features in backend services (Java and Spring Boot) and/or web (TypeScript).
• Own APIs and event-driven flows that move money, receipts, and policy decisions at company scale.
• Build or extend LLM-backed agents: tool use, grounding, streaming, session memory, retrieval, and evals.
• Improve document extraction and auto-itemization: quality, tax fields, latency, cost, and provider failover.
• Instrument production: observability, quality dashboards, chat satisfaction, extraction accuracy vs. human correction.
• Partner with Product and Design on employee, admin, and mobile AI surfaces (including unified travel-and-expense chat).
• Review for correctness in financial systems: idempotency, auditability, permissions, no silent partial writes.
• Mentor others and write designs that teams across time zones can implement from.

Conocimientos

Java/Spring Boot

TypeScript/Node.js

Python

APIs

Relational Databases

Kafka

AI/LLMs

Cloud Platforms

Communication

Herramientas

Docker

Kubernetes

PostgreSQL

Descripción del empleo

Navan is expanding Expense Engineering in Berlin and London to own the full expense lifecycle from receipts to GL. You will work on end-to-end expense product areas including international spend, tax receipts, policy, and audit, with AI-powered features already in the product.

You will design and ship backend services and web features, own APIs, and extend LLM-backed agents, with a focus on accuracy, latency, and safety across multi-entity setups.