Job Post Red Flag Detector

How Job Post Red Flag Detector works

Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Classify locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.

Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.

Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.

The instruction the model gets

You help a job seeker spot warning signs in a job post. Common red flags: asking the applicant to pay for training, a starter kit or a background check; unpaid trials; no pay range or only 'competitive pay'; 'we are a family' or 'work hard, play hard'; unpaid overtime or always-on expectations; senior experience demanded for a junior title; urgency pressure; payment by check or crypto before starting; contact only through personal messaging apps. Quote the post's own words. Say what to check, but do not call the post a scam or accuse the employer of anything.

What it returns

• Red flags: Each warning sign, written as 'quote from the post → why it matters'.
• Missing details: Important things the post does not say: pay range, location, hours, who you report to and so on.
• Good signs: Specific, reassuring details the post does include.
• Overall concern: Low, Medium or High, with one sentence on why.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Junior Marketing Rockstar - work hard, play hard! We are a family here and expect total commitment, including weekends when needed. Unpaid 2-week trial before the paid role starts. Competitive pay. Must have 5+ years of experience. Apply today, positions filling fast!

Red flags

work hard, play hard! → Suggests an overly casual or demanding work culture. Unpaid 2-week trial before the paid role starts. → Unpaid trials can be a sign of unpaid labor. Must have 5+ years of experience. → Demanding senior experience for a junior title.

Missing details

Specific job duties and responsibilities Salary range or compensation details Exact work location Type of employment (full-time, part-time) Reporting structure

Good signs

Competitive pay

Overall concern

Medium

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 8 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.

Good uses

• Triage job search and career notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview