About the role
Role Overview
As an AI Forward Engineer, you will operate at the intersection of deep software engineering, customer operations, and product strategy. Unlike standard back-office ML engineers who build foundational algorithms, you will be embedded on the front lines to solve real-world, high-impact business challenges.
You will work directly with enterprise stakeholders to identify operational bottlenecks, design custom AI solutions leveraging LLM tool-calling and RAG architectures, and integrate these systems into complex legacy infrastructure and Navan’s API suite.
What You’ll Do:
- Bridge Pilot-to-Production: Build, test, and ship production-ready AI agents and autonomous workflows that streamline travel booking, expense policy auditing, and financial reconciliation.
- Translate Business to Code: Engage directly with internal operational teams and external enterprise clients to audit complex manual workflows and codify "tribal knowledge" into custom software solutions.
- Architect & Integrate: Integrate advanced LLM pipelines, vector databases, and agentic frameworks into Navan’s core backend platforms, enterprise data lakes, and third-party ERP/HRIS systems (e.g., SAP, NetSuite, Workday).
- Rapid Prototyping & Feedback Loops: Develop proof-of-concepts (POCs) on-site or in close collaboration with end-users, gather real-time usage data, and iterate rapidly to maximize user adoption and business impact.
- Governance & Security: Ensure all custom AI solutions comply with strict enterprise data privacy standards, SOC 2 compliance, and financial auditing frameworks.
- Collaborate with Core Product Teams: Act as a critical feedback loop to Navan’s core Product and AI Engineering teams, bringing real-world edge cases and customer requirements into the core platform roadmap.
What We’re Looking For:
- 4+ years of experience in software engineering, technical consulting, forward deployed engineering, or solutions architecture.
- Experience in corporate travel, fintech, expense management, or enterprise SaaS domains are a plus.
- Familiarity with enterprise compliance, audit logs, and security protocols surrounding generative AI.
- Strong proficiency in Python, TypeScript/JavaScript, or Go, along with solid experience with REST/GraphQL APIs, microservices, and asynchronous architecture.
- Hands-on experience building with modern AI stacks (e.g., LangChain, LlamaIndex, OpenAI/Anthropic APIs), agentic architectures (tool-calling, multi-agent frameworks), and RAG pipelines (vector databases like Pinecone, Weaviate, or Qdrant).
- Proficiency in SQL, data pipeline integration, containerization (Docker, Kubernetes), and cloud deployment platforms (AWS, GCP, or Azure).
- Ability to design scalable, secure, and fault-tolerant enterprise software integrations.