New opportunity

Founding Applied AI Product Engineer

Spur · New York City, United States

About this role

Spur is hiring a Founding Applied AI Product Engineer in New York City to build autonomous browser agents that explore and validate digital experiences. The role combines end-to-end product engineering with applied AI for website quality assurance (QA). Spur’s platform uses natural language to create, run and maintain functional and regression tests, adapting to UI changes and integrating into CI/CD workflows.

Responsibilities

  • Design, code, deploy and own production features across the backend and performance-focused frontend.
  • Build and operate LLM-powered features and autonomous agents for self-healing testing automation.
  • Work directly with users, turn feedback into product improvements quickly, and help shape technical direction and product strategy alongside the founding team.

Qualifications

  • Strong TypeScript, Next.js and React expertise, with a track record of shipping production-grade features end to end.
  • Hands-on experience shipping applied AI or LLM products, including features powered by agents or large language models.
  • High autonomy, a founder’s mindset, interest in developer tools and a focus on user experience.

The stated compensation is $150k–$260k base plus meaningful equity. The role is on a team of 11 working on AI-powered QA automation.

For full details about this role, click “Apply on company site” to view the employer’s original posting.

Skills for this role

TypeScriptNext.jsReactLarge language modelsAI agentsBrowser automationFrontend developmentBackend developmentSoftware testingProduct development

Your skill match

Checking your profile…

YOUR NEXT STEP

Get interview-ready for this role

A focused preparation guide, built around this job’s responsibilities and requirements.

✦ AI-generated guide
Preparation suggestions, not the employer’s actual interview questions. Always check the original posting for current requirements.
01

Understand the role

What matters most

  • Own features from design to production

    Source-backed: The role owns end-to-end features across backend and performance-focused frontend, using TypeScript, Next.js, and React. Preparation suggestion: Be ready to explain production decisions across the full lifecycle, including deployment and frontend performance trade-offs.

  • Build and operate autonomous QA agents

    Source-backed: Spur seeks LLM-powered browser agents that explore and validate digital experiences, with self-healing testing automation. Preparation suggestion: Prepare a concrete account of how an applied-AI feature can be shipped, monitored, and improved in production.

  • Make automated tests useful in developer workflows

    Source-backed: The platform creates, runs, and maintains functional and regression tests from natural language, adapts to UI changes, and integrates into CI/CD. Preparation suggestion: Focus on how test results remain understandable and actionable as a product’s UI evolves.

  • Turn user feedback into product direction

    Source-backed: The engineer works directly with users, translates feedback into improvements within hours, and helps shape technical direction and product strategy alongside the founding team. Preparation suggestion: Be ready to describe how you would distinguish an urgent fix from a broader product change.

Likely challenges to think through

  • Adapt to UI changes without hiding failures

    Likely challenge, not a confirmed Spur problem: Self-healing tests must tolerate harmless UI changes without overlooking a real regression. Prepare to discuss how an agent might decide when to adapt, when to report uncertainty, and when to fail a test.

  • Balance rapid iteration with production reliability

    Likely challenge, not a confirmed Spur problem: Shipping improvements within hours while owning deployed features can create tension between speed and dependable behavior. Prepare to explain how you would scope a change, validate it, and observe its effects after release.

  • Convert varied feedback into a coherent roadmap

    Likely challenge, not a confirmed Spur problem: Direct user requests may pull an early-stage product in different directions. Prepare to explain how you would compare recurring user needs with engineering cost and the product’s QA focus before prioritizing work.

03

Practice your answers

Technical practice

How would you design an end-to-end feature for autonomous browser testing, from user request to production deployment?

What to coverThe role owns features from design and backend through a performance-focused frontend and deployment. Suggested preparation: explain the boundaries between test creation, agent execution, result reporting and the UI, including how you would make the feature operable in production.

How would an agent explore a website and decide what to validate?

What to coverSpur describes agents that explore and validate digital experiences. Suggested preparation: discuss how to choose actions, observe outcomes and distinguish a meaningful failure from an unexpected but acceptable page state.

How would you turn a natural-language request into a functional test?

What to coverThe platform lets teams create and run tests using natural language. Suggested preparation: describe how you would resolve ambiguity, represent the intended checks and make the resulting test understandable to a user.

How would you make a browser test adapt to a UI change without hiding a real regression?

What to coverAdapting to UI changes and reducing test maintenance are stated product goals. Suggested preparation: compare signals that justify updating a test with signals that warrant a failure, and explain how you would preserve user trust in the result.

How would you evaluate whether an LLM-powered testing agent is reliable enough to ship?

What to coverThe role includes building and operating LLM-powered features and agents. Suggested preparation: propose representative test scenarios and measures for correct findings, missed defects, false alarms and repeatability, then explain the trade-offs you would accept.

How would you design regression-test results for use in a CI/CD workflow?

What to coverThe page says the platform maintains regression tests and integrates into CI/CD workflows. Suggested preparation: explain what information a run should return to help a team decide whether to investigate or proceed, including how to present uncertain results.

How would you structure TypeScript code across a production feature's frontend and backend?

What to coverThe posting calls for strong TypeScript expertise and end-to-end feature ownership. Suggested preparation: discuss clear interfaces, validation at system boundaries and trade-offs between shared types and independently evolving components.

How would you keep a React and Next.js testing interface responsive as test activity and results grow?

What to coverReact, Next.js and a performance-focused frontend are explicit parts of the role. Suggested preparation: describe how you would identify the source of slowness and choose between rendering, data-loading and interaction improvements.

How would you investigate a production agent run that reports an unexpected test failure?

What to coverThe role involves operating agents and owning production features. Suggested preparation: walk through how you would separate a website regression from agent error or an environmental issue, and what evidence you would retain for debugging.

Behavioural practice

Tell me about a time direct user feedback changed a feature you were building.

What to coverThe role calls for working directly with users and turning feedback into product improvements quickly. For practice, use a real situation, explain what you changed and why, and give the result without overstating its impact.

Tell me about a feature you owned from design through production.

What to coverEnd-to-end ownership is central to the posting. For practice, describe the situation, your decisions and actions across the delivery stages, and the observed result.

Tell me about a time you set technical direction while product priorities were uncertain.

What to coverThe role offers scope to shape technical direction and product strategy alongside the founding team. For practice, give a real example of the uncertainty, how you weighed options and involved others, and what happened.

Tell me about a time you improved a developer-facing experience while balancing delivery speed and quality.

What to coverThe posting emphasizes developer tools, user experience and rapid iteration. For practice, describe the user problem, the trade-off you made, the action you took and the result you observed.

02

Sharpen your knowledge

Topics to prepare

  • End-to-end product architecture

    Posting: The role owns production features from backend through a performance-focused frontend. Revision exercise (suggestion): Sketch the data flow, deployment boundaries, and performance trade-offs for a feature that lets users review an agent-run test.

  • LLM agent behavior and reliability

    Posting: Spur builds and operates LLM-powered agents for autonomous browser testing and self-healing automation. Revision exercise (suggestion): Explain how an agent would decide what to inspect, verify an outcome, and respond when a UI change invalidates its previous approach.

  • Functional and regression testing

    Posting: Spur’s platform creates, runs, and maintains website tests from natural language, adapts to UI changes, and is designed to integrate into CI/CD workflows. Revision exercise (suggestion): Compare a functional test with a regression test, then outline how to distinguish a genuine failure from a changed interface.

  • Customer-led product decisions

    Posting: The engineer works directly with users, turns feedback into improvements quickly, and helps shape technical direction. Revision exercise (suggestion): Take a hypothetical complaint about an unreliable test result and explain what you would clarify with the user, prioritize, and change.

Skills to revise

  • Build a TypeScript, Next.js, and React feature

    Posting: Strong expertise in all three is specified, alongside shipping production-grade features end to end. Revision exercise (suggestion): Implement a small test-run results view with a backend endpoint, typed data, loading and error states, and a concise explanation of frontend performance choices.

  • Implement an LLM-powered agent loop

    Posting: Hands-on experience shipping applied AI or LLM features, including agents, is specified. Revision exercise (suggestion): Write pseudocode or a small implementation that takes a natural-language testing goal, chooses a browser action, checks the observed result, and handles an unsuccessful step.

  • Handle changing interfaces in a test flow

    Posting: The product aims to maintain tests as UIs change through self-healing automation. Revision exercise (suggestion): Walk through a test whose target control has moved or changed label; show how you would attempt recovery and when you would report a failure rather than silently pass.

  • Turn user feedback into a shippable change

    Posting: The role calls for direct user engagement and rapid iteration alongside the founding team. Revision exercise (suggestion): Draft a brief plan for addressing one piece of QA-user feedback: define the problem, select a small change, state how you would validate it, and describe its path to production.

04

Your preparation checklist

  • Prepare an end-to-end feature walkthrough

    Choose a feature you actually shipped and map its design, TypeScript implementation, backend and React or Next.js frontend, deployment, and production ownership. These reflect the role’s stated responsibilities and qualifications.

  • Document an applied AI example

    If you have shipped an LLM- or agent-powered feature, prepare a concise account of its behavior, your contribution, and how you operated it after release. The posting specifically asks for hands-on shipping experience.

  • Sketch a browser-agent QA design

    As a practice exercise, diagram how a natural-language test could explore a website, validate behavior, adapt to a UI change, and report results in CI/CD. Mark this as a proposed design, not Spur’s implementation.

  • Prepare a frontend trade-off discussion

    Bring a concrete example of a React or Next.js decision you made, including its user-experience or performance trade-off and the result. Spur calls for a performance-focused frontend and attention to user experience.

  • Rehearse a feedback-to-release story

    Outline a real instance, if available, where user feedback changed a product decision: what you heard, what you prioritized, what shipped, and what you learned. The role involves rapid iteration with users and the founding team.

  • Write questions for Spur

    Prepare questions about how the team evaluates agent reliability, handles UI changes in tests, decides what to improve from user feedback, and divides product ownership. These are questions to ask, not claims about Spur’s current processes.

AI-generated from the job information · Prepared Sep 30, 2026 (UTC)Useful preparation, not a guarantee of eligibility or an offer.

Availability last checked: Nov 4, 2026. Status can change after a check; confirm on the employer’s website. Report an issue · Our checking policy

KEEP EXPLORING

Similar AI jobs

Related skills and specializations in United States. Matched to this role, not your profile.

Explore more jobs
Finding similar opportunities…