> Markdown version of [/jobs/ext/1919241-web-browsing-task-evaluator](https://www.wearedevelopers.com/jobs/ext/1919241-web-browsing-task-evaluator). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md).

---

# Web Browsing Task Evaluator

- **Company:** AuraOne Human Data
- **Location:** United States (Remote available)
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Web Browsers
- **Published:** August 4, 2026
- **Apply:** https://www.indeed.com/viewjob?jk=cc0ef1f805273071

## About the Role

* Prior evaluation, annotation, or human-rater experience on web browsing task evaluation or adjacent content for Web Browsing Task Evaluator work.
 * Comfort applying multi-page rubrics consistently across long batches.
 * Clear written reasoning that names the issue and the rubric clause being applied.
 * Strong attention to detail and the ability to flag when a prompt itself is the problem.
 * Reliable async availability for at least 10 hours per week., * Background in linguistics, content moderation, or trust & safety review.
 * Experience with inter-rater agreement metrics and calibration cycles.
 * Domain expertise that lets you spot subject-matter errors automated checks miss., * Model output evaluation
 * Rubric-based annotation
 * Severity tagging
 * Inter-rater calibration
 * Web Browsing Task evaluation
 * Web research
 * Source grounding
 * Browser automation
 * Browsing

Work model

Remote - US-eligible. Remote · Independent specialist contractor. Employment type: CONTRACTOR. Applicants must be authorized to work from US.

## Description

Web Browsing Task Evaluator is a remote evaluation track for reviewing web browsing task evaluation prompts and responses against AuraOne's quality rubric. Reviewers compare paired outputs, label edge cases, and write the kind of structured feedback the modeling team can use to retrain.

Why this role matters

AI data reviewers help turn web browsing task evaluation outputs into auditable labels, rationales, and regression cases for AuraOne Human Data.

Responsibilities

 * Evaluate web browsing task evaluation model outputs against a versioned rubric and assign severity tags for Web Browsing Task Evaluator assignments.
 * Compare paired responses and pick the stronger answer with a written rationale.
 * Label hallucinations, instruction-following failures, and unsafe content with structured tags.
 * Capture ambiguous prompts and route them back to the program team for rubric updates.
 * Maintain reviewer-quality scores by calibrating against gold-standard examples each week.
 * Document recurring failure modes so the modeling team can target them in the next training run., * Tag an unsafe response with the correct policy category and severity.
 * Audit a 50-row batch for rubric consistency and report drift to the program lead.
 * Propose a rubric clarification after spotting a recurring failure mode.


## Related Videos

- [How Web AI Can Power the Agentic Web - Jason Mayes (Google)](https://www.wearedevelopers.com/videos/1896-how-web-ai-can-power-the-agentic-web-jason-mayes-google)
- [Edit Your Future: Queerverse Radical AI](https://www.wearedevelopers.com/videos/909-edit-your-future-queerverse-radical-ai)
- [Decoding web accessibility through audit](https://www.wearedevelopers.com/videos/507-decoding-web-accessibility-through-audit)
- [Privacy-first in-browser Generative AI web apps: offline-ready, future-proof, standards-based](https://www.wearedevelopers.com/videos/1572-privacy-first-in-browser-generative-ai-web-apps-offline-ready-future-proof-standards-based)
- [Developer Time Is Valuable - Use the Right Tools - Kilian Valkhof](https://www.wearedevelopers.com/videos/1792-developer-time-is-valuable-use-the-right-tools-kilian-valkhof)
- [AI is dead, long live AK](https://www.wearedevelopers.com/videos/1093-ai-is-dead-long-live-ak)

## Related Articles

- [Dev Digest 133 - Back to Front](https://www.wearedevelopers.com/magazine/474-dev-digest-133-back-to-front)
- [The Web We Broke (And Why AI Agents Are Paying the Price) - AgentCon Berlin](https://www.wearedevelopers.com/magazine/735-the-web-we-broke-and-why-ai-agents-are-paying-the-price-agentcon-berlin)
- [WebMCP: Empowering Agents as First-Class Citizens of the Web](https://www.wearedevelopers.com/magazine/696-webmcp-empowering-agents-as-first-class-citizens-of-the-web)
- [13 AI Tools You Have to Try](https://www.wearedevelopers.com/magazine/219-13-ai-tools-you-have-to-try)
- [Dev Digest 119 - ❤️ === ❤️](https://www.wearedevelopers.com/magazine/454-dev-digest-119)
- [How Developers Can Focus on Maintaining Satisfaction With Accessibility](https://www.wearedevelopers.com/magazine/109-how-developers-can-focus-on-maintaining-satisfaction-with-accessibility)