Schema Alignment Data Specialist

AuraOne Human Data
United States
about 1 month ago
Apply on www.indeed.com
Prepare application

Role details

Contract type
Permanent contract
Employment type
Part-time (≤ 32 hours)
Working hours
Regular working hours
Job source

Tech stack

Artificial Intelligence Data Auditing Bug Reporting

Job description

Schema Alignment Data Specialist is a remote red-team track for stress-testing AI systems against adversarial prompts. Reviewers craft attack scenarios, document the failure mode, and pair each successful jailbreak with the rubric clause it violated so the safety team can patch the gap.

Why this role matters

Adversarial evaluation is how AuraOne hardens AI models before they ship to customers. Reviewers think like attackers and write up failures with enough rigor that the modeling team can reproduce, fix, and regress-test them., * Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for Schema Alignment Data Specialist assignments.

  • Document every successful attack with reproduction steps and the policy clause it violated.
  • Score model defenses across single-turn and multi-turn conversations.
  • Triage emerging attack vectors and route them to the safety team with severity ratings.
  • Maintain a personal library of attack patterns and propose new red-team rubrics.
  • Calibrate against the broader red-team cohort to keep coverage and severity consistent.

Requirements

  • Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for Schema Alignment Data Specialist work.
  • Strong written communication - your reports become the patch ticket.
  • Comfort working in policy-grey areas with clear documentation of what was attempted and why.
  • Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.
  • Reliable async availability for at least 10 hours per week., * Background in offensive security, AppSec, or trust & safety operations.
  • Experience publishing or reproducing public adversarial-ML research.
  • Multilingual fluency for cross-language attack testing., * Adversarial prompting
  • Red-team analysis
  • Policy taxonomy
  • Failure documentation
  • Schema Alignment Data evaluation
  • Data quality
  • Taxonomy design
  • Ontology review
  • Schema
  • Alignment

Work model

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

Benefits & conditions

  • Construct a 5-turn adversarial conversation that bypasses a specific policy clause and write up the patch ticket.
  • Score a model’s defenses against a known jailbreak pattern across 20 variants.
  • Propose a new red-team rubric category after spotting an emerging attack vector.
  • Reproduce a failure another reviewer reported and confirm the severity tag., Hourly rate confirmed after the interview process.

Apply for this position

This job is hosted externally. Click below to view the full posting and apply.

Apply on www.indeed.com
Prepare application

Good distractions

Talks and stories from around this role — technically off-topic, practically not.

1:33 min

Designing modular AI architectures for data sovereignty

Markus Hacker Markus Hacker +1 · World Congress 2025

3:16 min

Advantages of reproducible configurations and instantaneous rollbacks

Álvaro Martín Lozano · LIVE

5:19 min

Identifying vulnerabilities and automating Jira bug reports

Sergio Freire Sergio Freire · Europe 2026 Virtual

3:46 min

Core terminology and audiences for interpretable artificial intelligence

Karol Przystalski · LIVE

3:09 min

Balancing data science skillings alongside systems engineering rigor

Nico Schmidt · LIVE

3:08 min

Conducting data audits and adversarial testing on models

Toju Duke · World Congress 2022

Videos

See all

Related articles

See all