> Markdown version of [/jobs/ext/3900304-frontend-code-evaluation-specialist](https://www.wearedevelopers.com/jobs/ext/3900304-frontend-code-evaluation-specialist). 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).

---

# Frontend Code Evaluation Specialist

- **Company:** Mercor, Inc.
- **Location:** New York, NY, United States (Remote available)
- **Experience:** Experienced
- **Salary:** $187,200.0
- **Contract:** Permanent contract
- **Skills:** JavaScript (Programming Language), Artificial Intelligence, Cascading Style Sheets (CSS), Command-Line Interface, Code Generation, Web Scraping, Web Development, Semantic HTML, Large Language Models, Pixel Perfect, Front End Software Development
- **Published:** October 23, 2026
- **Apply:** https://www.thejobnetwork.com/job/078943a9-46d9-46a7-a393-5200556fd05c/frontend-code-evaluation-specialist

## About the Role

Must-Have

 * 3-8 years of professional web development experience in frontend or full-stack work.
 * Fluency across web eras, including legacy layouts like used for layout.
 * Command of hand-written HTML and CSS: semantic markup, flexbox, grid, media queries, and legacy float- and table-based layouts.
 * Browser DevTools as muscle memory.
 * Command-line comfort: unzipping an archive, standing up a static local server, and untangling a broken image reference.
 * Enough JavaScript to read a page's scripts and understand their DOM impact.
 * Professional written English for task justification.

Preferred

 * Prior RLHF, preference-labeling, model-evaluation, or structured code-review work.
 * Pixel-perfect design-to-code experience.
 * Accessibility expertise (ARIA, semantic landmarks, heading hierarchy).
 * Familiarity with how LLMs fail at code generation.
 * Web scraping, archiving, or DOM-parsing background.
 * More than one completed Mercor project and availability in contiguous multi-hour blocks.

## Description

* Render a reference page and two candidate replications at 1920×1080. Judge which is the closer reproduction, state by state.
 * Diff visual fidelity in detail: box model and spacing, typography (family, size, weight, line-height, letter-spacing), color and border treatment, image and asset handling, z-order, and overflow.
 * Read the source of both attempts and grade construction quality. Distinguish a replication that is genuinely correct from one that merely looks correct at one viewport.
 * Test responsiveness. Identify defects such as a nav bar that looks right at 1920px but collapses at 1400px.
 * Write specific, evidence-cited justifications for every preference. Provide detailed explanations like "B nests the article body in a single absolutely-positioned div, so the text overlaps the footer below 1600px, while A uses normal document flow."
 * Use the "this task is broken" escape hatch with judgment. Distinguish a task that genuinely cannot be completed from one that is merely hard., PS: Our team reviews applications daily. Please complete your AI interview and application steps to be considered for this opportunity.