Navan
Navan

AI Forward Engineer

$113–252kPalo Alto, CA; San Francisco, CA; New York, NY, USHybridMidFull-time

Posted 2 days ago

The role in short

Embed with enterprise clients to design, build, and deploy production AI agents and integrations for travel and expense workflows.

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.

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.

About Navan

Navan (Nasdaq: NAVN) is the global AI-powered business travel and expense platform that makes travel easy for frequent travelers. From finding flights and hotels, to automating expense reconciliation, with 24/7 support along the way, Navan delivers an intuitive experience travelers love and finance teams rely on. See how Navan customers benefit and learn more at navan.com.

Culture of Excellence

Our team is our competitive edge — a high-performance group of smart, driven people committed to winning together. This dedication to excellence is why we’ve been recognized as a Best Place to Work by Built In (2023–2026), a G2 Best Global Software Company (2025–2026), Forbes Cloud 100 (2022–2025), and CNBC Disruptor 50 (2022–2025). At Navan, we provide an environment where top talent excels, offering the autonomy and fast-paced trajectory needed to build a defining career and do the best work of your life.

Our Benefits

Navan offers a comprehensive benefits program designed to support your well-being, financial security, and life outside of work. Our benefits, thoughtfully tailored by country to meet local needs, include healthcare coverage, insurance offerings, and wellness resources for you and your family.

We support long-term financial growth through retirement savings programs and opportunities to participate in our equity plans, so you can share in Navan’s success. To promote balance, we offer flexible time off, country-specific holidays, and paid parental leave for all new parents. Additional benefits include connectivity and commuting support*, mental health resources, and exclusive travel-related perks. Wherever you’re based, our benefits evolve with you.

Workplace Policy

Navan believes in the value of in-person connections, whether that’s sitting down to have lunch with one another, taking a walking 1:1, or collaborating in a room together. The connections forged through face-to-face interactions improve company culture and drive business results. Navan invests in global office spaces — in the U.S., Europe, and Asia, among others — that feel welcoming. In-office perks such as company-provided lunches and happy hours create a strong team environment to help you do your best work. Our employees work from the office four days a week. Please expect this policy for all roles that are tied to an office.

Equal Opportunity

Navan is an equal opportunity employer. We make all employment decisions based solely on merit. We provide equal employment opportunity to all applicants and employees without discrimination on the bases of race, religion, color, national origin, gender (including pregnancy, childbirth, or related medical conditions), sexual orientation, gender identity, gender expression, age, status as a protected veteran, status as an individual with a disability, or other applicable legally protected characteristics. We prohibit any such discrimination or harassment. This policy applies to all terms and conditions of employment, including hiring.

Accommodations

Navan complies with the Americans with Disabilities Act (ADA), as amended by the ADA Amendments Act, and all applicable state or local law. Navan will reasonably accommodate qualified individuals with a disability in connection with applications for employment as required by law.

If you need any assistance or accommodations due to a disability, you are welcome to email us at talent-accommodations@navan.com.

Candidate Privacy Notice and Use of AI

As part of the recruitment process, certain personal data may be processed using automated tools, including tools that use AI. For details on how Navan collects and uses your personal data, please review Navan's Candidate Privacy Notice here.

Job Search Best Practices

We have been made aware of recruitment scams involving fraudulent attempts to lure job seekers into sending money or personal information in return for fake job offers or coerce them into purchasing equipment by electronic funds transfer (Zelle, Venmo, etc.) Legitimate Navan recruiters will never ask for money in any recruitment or onboarding activities. All available job openings at Navan will be posted on Navan’s website and all Navan recruiters will be reachable through an email address ending in “@navan.com” or “@navan.tech” or "@talent.navan.com".

*Applies to select locations.

Prep for this interview

5 questions likely to come up at Navan, each matched to a line in this posting.

  1. 1Data and SQL
    They wrote: “Proficiency in SQL, data pipeline integration, containerization ( Docker, Kubernetes), and cloud deployment platforms ( AWS, GCP, or Azure).”

    Write a query that finds each customer's first and most recent order.

    How to answer

    Why they ask: A quick check that you're comfortable with grouping, joins and window functions.

    1. Clarify the tables and what counts as an order (cancelled ones?)
    2. Use MIN/MAX with GROUP BY, or ROW_NUMBER() if you need the whole row
    3. Handle ties on the same timestamp, and customers with no orders
    4. Explain how you'd test it on a few known customers

    Tip: Say what you'd check in the data before writing the query: duplicates, time zones, nulls.

  2. 2Cloud, deployment and security
    They wrote: “Governance & Security: Ensure all custom AI solutions comply with strict enterprise data privacy standards, SOC 2 compliance, and financial auditing frameworks.”

    The customer's security team sends a 200-question review. How do you handle it?

    How to answer

    Why they ask: Security reviews often block deals. FDEs help get through them.

    1. Start from your company's standard answers (SOC 2 report, past reviews)
    2. Answer clearly; don't oversell
    3. Bring in your security team for anything you're unsure of
    4. Keep the new answers for the next customer

    Tip: Reuse past answers, flag honest gaps, and offer a call for the hard questions.

  3. 3Discovery and scoping
    They wrote: “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.”

    How do you decide what to build first when a customer wants ten things?

    How to answer

    Why they ask: FDEs have limited weeks per customer. This tests judgment about value, effort and risk.

    1. Score each request by business value and by effort, with the customer in the room
    2. Pick one item that proves value fast and unblocks later work
    3. Write down what's out of scope so it doesn't creep back in
    4. Revisit the list after the first release, with real usage data

    Tip: Show a simple way to rank the list and name what you'd leave out on purpose.

  4. 4Integrations and APIs
    They wrote: “Strong proficiency in Python, TypeScript/JavaScript, or Go, along with solid experience with REST/GraphQL APIs, microservices, and asynchronous architecture.”

    Walk me through connecting our product to a customer's internal system that has no documentation.

    How to answer

    Why they ask: This happens weekly in the job. They want a calm, step-by-step method.

    1. Find who owns the system and get read access to a test environment
    2. Watch real traffic or logs to learn the data shapes
    3. Build a thin adapter with logging around every call
    4. Agree on how failures get reported, and who fixes what

    Tip: Talk about finding the owner of the system first. The code is the easy part.

  5. 5LLMs, RAG and agents
    They wrote: “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.”

    A customer wants a chatbot over their internal documents. How do you build it?

    How to answer

    Why they ask: RAG is the most common first project. They want the whole path, from messy files to answers people trust.

    1. Collect and clean the documents; handle permissions per user
    2. Split them into chunks, embed, and store with source links
    3. Retrieve, then answer with citations; say “I don't know” when retrieval is weak
    4. Build a test set of real questions with expected answers before launch

    Tip: Spend more time on the data and on testing than on the model.

Not the one? Get the next one by email

New roles land here every day. Pick what you want to hear about.

FDE Info

Want the job, not just the posting? Learn how FDEs work.

FDE Info is our free weekly newsletter for forward deployed engineers: tools, field notes from real deployments, and how FDE teams hire and pay.

Free. One email a week. Unsubscribe in one click.

Similar roles at other companies

Navan

$113–252k · Hybrid

Apply