> Markdown version of [/jobs/ext/1917550-sandbagging-detection-model-evaluation-specialist](https://www.wearedevelopers.com/jobs/ext/1917550-sandbagging-detection-model-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).

---

# Sandbagging Detection Model Evaluation Specialist

- **Company:** AuraOne Human Data
- **Location:** United States (Remote available)
- **Contract:** Permanent contract
- **Skills:** Artificial Intelligence, Model Validation
- **Published:** August 4, 2026
- **Apply:** https://www.indeed.com/viewjob?jk=245845d4f6793f7b

## About the Role

* Prior evaluation, annotation, or human-rater experience on sandbagging detection model evaluation evaluation or adjacent content for Sandbagging Detection Model Evaluation Specialist 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
 * Sandbagging Detection Model Evaluation evaluation
 * Frontier evaluation
 * Rubric calibration
 * Failure analysis
 * Sandbagging
 * Detection

Work model

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

## Description

Sandbagging Detection Model Evaluation Specialist is a remote evaluation track for reviewing sandbagging detection model evaluation 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 sandbagging detection model evaluation evaluation outputs into auditable labels, rationales, and regression cases for AuraOne Human Data., * Evaluate sandbagging detection model evaluation evaluation model outputs against a versioned rubric and assign severity tags for Sandbagging Detection Model Evaluation Specialist 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

- [Introduction to Responsible AI: Balancing Value and Risk](https://www.wearedevelopers.com/videos/1972-introduction-to-responsible-ai-balancing-value-and-risk)
- [Edit Your Future: Queerverse Radical AI](https://www.wearedevelopers.com/videos/909-edit-your-future-queerverse-radical-ai)
- [Stop Guessing, Start Measuring: Evaluating RAG Systems with Synthetic Test Data](https://www.wearedevelopers.com/videos/1982-stop-guessing-start-measuring-evaluating-rag-systems-with-synthetic-test-data)
- [Hack Me If You Can: Designing Unbreakable LLM Guardrails](https://www.wearedevelopers.com/videos/100209-hack-me-if-you-can-designing-unbreakable-llm-guardrails)
- [AI is dead, long live AK](https://www.wearedevelopers.com/videos/1093-ai-is-dead-long-live-ak)
- [Building Trustworthy AI in Industry: Beyond Traditional Cybersecurity](https://www.wearedevelopers.com/videos/1948-building-trustworthy-ai-in-industry-beyond-traditional-cybersecurity)

## Related Articles

- [Dev Digest 121 - AI goes offline](https://www.wearedevelopers.com/magazine/456-dev-digest-121-ai-goes-offline)
- [Is Software Engineering Over-Saturated?](https://www.wearedevelopers.com/magazine/418-is-software-engineering-over-saturated)
- [Dev Digest 119 - ❤️ === ❤️](https://www.wearedevelopers.com/magazine/454-dev-digest-119)
- [Dev Digest 134 - Where pixels sing?](https://www.wearedevelopers.com/magazine/477-dev-digest-134-where-pixels-sing)
- [The Best Job Search Websites of 2025](https://www.wearedevelopers.com/magazine/368-the-best-job-search-websites-of-2025)
- [Dev Digest 120 - Apple and peers](https://www.wearedevelopers.com/magazine/455-dev-digest-120-apple-and-peers)