Sr. Software Engineer, Core AI

Navan • New York, NY

2d • $113,400 - $252,000

About The Position

Navan is building specialized AI services to improve high-value human workflows across the company. The Senior Software Engineer, Core AI will design, build, evaluate, and operate production-grade AI services and agents, owning work end to end—from data and context design through tool use, application logic, evaluation, and production monitoring. The role involves delivering task-specific AI services, defining and measuring expected behavior, improving quality based on evaluations and production feedback, and integrating reliability and observability practices. The engineer will collaborate with AI Architecture, AI Ops, and Platform teams to develop secure, reliable, cost-aware services that can be deployed at scale, and will iteratively move solutions from user problem to prototype to production.

Requirements

• 5+ years of strong software engineering experience delivering production services or products.
• Hands-on experience building AI/LLM-powered applications or agents used by real users or in operational settings.
• Experience evaluating AI behavior, including defining expected outcomes, building test sets or evaluations, tracking regressions, and acting on results.
• Ability to shape retrieval, context, and serialization so models have the information needed for a task.
• Good judgment regarding tool use, autonomy, human review, failure handling, privacy, reliability, latency, and cost.
• A product-minded approach focused on solving specific workflow problems and measuring whether solutions work.

Nice To Haves

• Experience at a senior or staff level.
• Experience with agent runtimes, model APIs, MCP, tracing, or evaluation tools.

Responsibilities

• Design and implement task-specific AI services and agents, including data serialization, retrieval, memory where appropriate, tool integrations, and bounded multi-step reasoning.
• Work with partners to define expected behavior and create and maintain evaluations based on representative examples.
• Use evaluation results to measure service performance against expectations.
• Improve context, data, service logic, tools, and model behavior using evaluation findings, failure analysis, and production feedback.
• Integrate tracing, observability, versioning, monitoring, reliability practices, and success metrics into owned services.
• Run controlled, repeatable experiments comparing models, data, and implementation approaches.
• Partner with AI Architecture, AI Ops, and Platform teams to make services secure, reliable, cost-aware, and deployable at scale.
• Iterate from user problem to prototype to production, using real workflow outcomes to guide improvements.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed