Senior Backend Engineer - NavanCognition.ai

We are seeking a skilled Senior Backend Engineer to join our team and help us build Navan Cognition, a multi-agent AI platform. The ideal candidate will have strong backend engineering expertise and enthusiasm for working with cutting-edge AI technologies.

About the Role:
You'll be responsible for designing and implementing backend services that integrate AI capabilities including large language models (LLMs), retrieval-augmented generation (RAG), and conversational interfaces into our consumer-facing products. This is an opportunity to expand your expertise into AI while leveraging your strong engineering foundation.

What You'll Do

Design and develop scalable, high-performance backend services and APIs
Implement integrations with AI platforms and services
Work with AI specialists to translate AI capabilities into production-ready features
Ensure high reliability, performance, and security of AI-powered systems
Collaborate with product and engineering teams to gather requirements and deliver solutions

What We're Looking for:

Proven Backend Expertise: 5+ years of professional experience, with a strong foundation in building and maintaining robust backend systems for large-scale consumer or enterprise products.
Technical Mastery: Advanced proficiency in at least one modern backend language (TypeScript and Node.js), with hands-on experience developing production-grade APIs and microservices. Experience with Lambda functions is a big plus.
Scalable Systems Builder: Demonstrated experience architecting and delivering high-availability services and distributed systems, leveraging patterns for reliability, performance, and security.
Cloud-Native Engineering: Deep familiarity with cloud platforms (AWS, GCP, or Azure), including hands-on experience with serverless technologies (e.g., AWS Lambda), infrastructure-as-code, and automated deployment pipelines.
Data Fluency: Solid experience with both SQL and NoSQL databases; knowledge of vector databases and embedding/search technologies is a big plus.
AI Platform Integration: Experience integrating with modern AI services (OpenAI, Hugging Face, etc.), and enthusiasm for collaborating with ML/AI specialists to bring LLMs, RAG, and conversational AI capabilities into production.
SRE / Reliability Focus: Strong understanding of operational excellence–monitoring, observability, incident response, and designing for system resiliency at scale.
Results-Oriented Delivery: A track record of shipping consumer-facing features at scale, collaborating closely with both product and engineering teams.

Forward-Thinking Problem Solver: Eager to explore new technologies, solving complex problems using both solid engineering fundamentals and innovative approaches.