Sr. Software Engineer, Core AI

Navan
New York, NY

In the 12 months to 30 Jun 2026, Navan filed 6 H-1B positions titled "Senior Software Engineer". Source: U.S. Department of Labor, LCA disclosure data. A record of filings already made, not a commitment to sponsor.

Who this role is best for

Strong fit for software engineers with AI/LLM experience who design and operate production-grade AI services and focus on solving specific workflow problems.

Best fit for

  • Candidates with 5+ years of experience in building AI/LLM-powered applications for real users
    — “Hands-on experience building AI/LLM-powered applications or agents with real users or operational use”
  • Individuals who can systematically improve AI quality through evaluation and feedback loops
    — “Improve quality systematically: use evaluation findings, failure analysis, and production feedback to improve context and data, service logic, tools, and model behavior.”
  • Candidates who prioritize production readiness with observability, versioning, and reliability practices
    — “Build for production: integrate tracing, observability, versioning, monitoring, reliability practices, and success metrics into the services you own.”

Things to consider

  • The role requires a strong ability to define and measure expected AI behavior using representative examples.
    — “Define and evaluate quality: work with partners to make expected behavior explicit, write and maintain evals against representative examples”
  • Candidates must be prepared to work closely with AI Architecture, AI Ops, and Platform teams on service deployment.
    — “Partner on architecture: work with AI Architecture, AI Ops, and Platform teams to make services secure, reliable, cost-aware, and deployable at scale.”

How to stand out

  • Highlight experience in building AI services with end-to-end ownership and measurable success metrics.
    — “own work end to end—from data and context design through tool use, application logic, evaluation, and production monitoring.”
  • Emphasize your ability to shape retrieval and context design to optimize model performance.
    — “A data-first mindset: able to shape retrieval, context, and serialization to give a model the information needed for the task.”
  • Showcase your experience with evaluation methods and how you use them to drive AI improvements.
    — “Experience with evaluation methods for AI behavior: defining expected outcomes, building test sets or evals, tracking regressions, and acting on results.”
Pace · Fast PacedCollaboration · HighAutonomy · HighDecision Impact · Team

Derived from job-description analysis by Serendipath's career intelligence engine.

What success looks like

  • design and implement task-specific services and agents
  • define and evaluate quality
  • improve quality systematically
  • build for production
  • run controlled experiments
Typical background
software engineerAI researcherdata scientist

Skills & requirements

Required

5+ Years Of Strong Software Engineering ExperienceHands-on Experience Building Ai/llm-powered Applications Or AgentsExperience With Evaluation Methods For AI BehaviorAbility To Shape Retrieval, Context, And Serialization To Give A Model The Information Needed For The TaskGood Judgment About Tool Use, Autonomy, Human Review, Failure Handling, Privacy, Reliability, Latency, And CostProduct-minded Approach Focused On Solving Specific Workflow Problems And Measuring Whether The Solution Works

Preferred

Experience With Agent Runtimes, Model Apis, MCP, Tracing, Or Evaluation Tools

Stack & domain

AI ServicesLlm-powered ApplicationsEvaluation Methods For AI BehaviorData-first MindsetTool UseProduct-minded ApproachGood JudgmentLearning Tools And FrameworksAISoftware Engineering

About the role

Original posting from Navan

About the Role

We are building a fleet of specialized AI services that improve high-value human workflows across the company. As a Senior Software Engineer, Core AI, you will design, build, evaluate, and operate production-grade AI services and agents. You will own work end to end—from data and context design through tool use, application logic, evaluation, and production monitoring.

What You’ll Do:

Build specialized AI services: design and implement task-specific services and agents, including data serialization, retrieval, memory where appropriate, tool integrations, and bounded multi-step reasoning.

Define and evaluate quality: work with partners to make expected behavior explicit, write and maintain evals against representative examples, and use results to measure performance against expectations.

Improve quality systematically: use evaluation findings, failure analysis, and production feedback to improve context and data, service logic, tools, and model behavior.

Build for production: integrate tracing, observability, versioning, monitoring, reliability practices, and success metrics into the services you own.

Run controlled experiments: compare models, data, and implementation approaches using repeatable benchmarks so improvements are attributable and reproducible.

Partner on architecture: work with AI Architecture, AI Ops, and Platform teams to make services secure, reliable, cost-aware, and deployable at scale.

Ship iteratively: move quickly from user problem to prototype to production, learning from real workflow outcomes.

What We’re Looking For:

5+ years of strong software engineering experience delivering production services or products, ideally at senior or staff level.

Hands-on experience building AI/LLM-powered applications or agents with real users or operational use.

Experience with evaluation methods for AI behavior: defining expected outcomes, building test sets or evals, tracking regressions, and acting on results.

A data-first mindset: able to shape retrieval, context, and serialization to give a model the information needed for the task.

Good judgment about 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 the solution works.

Comfort learning tools and frameworks; experience with agent runtimes, model APIs, MCP, tracing, or evaluation tools is helpful.

The posted pay range represents the anticipated low and high end of the compensation for this position and is subject to change based on business need. To determine a successful candidate’s starting pay, we carefully consider a variety of factors, including primary work location, an evaluation of the candidate’s skills and experience, market demands, and internal parity.

For roles with on-target-earnings (OTE), the pay range includes both base salary and target incentive compensation. Target incentive compensation for some roles may include a ramping draw period. Compensation is higher for those who exceed targets. Candidates may receive more information from the recruiter.Pay Range$113,400—$252,000 USD 

Navan uses AI-assisted Automated Employment Decision Tool (Metaview) to assist with evaluating resumes against job qualifications for this role. All final decisions are made by human recruiters and hiring managers. 

Human oversight: Metaview does not automatically reject candidates or make final hiring decisions. Our recruiters and hiring managers review all outputs and make the final hiring decision regarding every application. 

Your rights: If you prefer to have your application reviewed without AI assistance, you may request a human evaluation by entering your email here. Your decision to do so will not affect how your candidacy is evaluated. 

Please refer to our Candidate Privacy Notice for more information about our processing of personal data, and your rights.

Source: Navan careers

Similar roles

More roles at Navan