English AI Safety Specialist

AuraOne, Inc.; United States; Remote; USD 39,000 - 44,000; Part time

Job summary

AuraOne, Inc. is seeking an English AI Safety Specialist to remotely stress-test AI systems with adversarial prompts. You will design jailbreak scenarios, document failures with exact steps, and map each breach to the applicable policy clause to guide patches.

The role emphasizes rigorous writing, reproducible workflows, and collaboration with a safety team. This contractor position offers flexible hours and US eligibility for remote work.

Qualifications

• Experience in red-teaming AI systems, security research, or adversarial ML work is required.
• Strong written communication; reports become patch tickets.
• Ability to document what was attempted and why in policy-grey areas.

Responsibilities

• Design adversarial prompts to probe known weakness classes.
• Document every successful attack with reproduction steps and violated policy clause.
• Score model defenses across single-turn and multi-turn conversations.
• Triage emerging attack vectors and route them to safety with severity ratings.
• Maintain a library of attack patterns and propose new red-team rubrics.
• Calibrate against the broader red-team cohort for consistency.

Skills

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

English AI Safety evaluation

Job description

English AI Safety 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.

Responsibilities

• Design adversarial prompts that probe known weakness classes (jailbreak, policy bypass, prompt injection) for English AI Safety 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.

Qualifications

• Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for English AI Safety 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.

Example tasks

• 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.

Nice to have

• Background in offensive security, AppSec, or trust & safety operations.
• Experience publishing or reproducing public adversarial-ML research.
• Multilingual fluency for cross-language attack testing.

Skills

• Adversarial prompting
• Red-team analysis
• Policy taxonomy
• Failure documentation
• English AI Safety evaluation

Work model

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

Compensation

$30 / hr

Demonstrated experience red-teaming AI systems, security research, or adversarial ML work for English AI Safety 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.