AI Safety Experts — English & Assamese

AuraOne; United States; Sur place; USD 28 000 - 30 000; Plein temps

Résumé du poste

AI Trainer Jobs is seeking AI Safety Experts — English & Assamese for a remote contractor role. You will craft adversarial prompts, document failures, and pair each successful jailbreak with the violated rubric clause to help patch gaps.

You will design 5-turn scenarios, score defenses, and triage new attack vectors with severity ratings. Multilingual fluency for cross-language testing is valued.

Qualifications

• Experience red-teaming AI systems or adversarial ML.
• Strong written communication in reports and documentation.
• Comfort documenting what was attempted and why.
• Familiarity with prompt-injection, jailbreak, and policy-bypass taxonomies.
• Reliable availability for at least 10 hours per week.

Responsabilités

• Design adversarial prompts to probe known weakness classes for English & Assamese 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.

Connaissances

Adversarial prompting

Red-team analysis

Policy taxonomy

Failure documentation

Multilingual testing

Description du poste

About the role

AI Safety Experts — English & Assamese 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.
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.
Push on refusal boundaries and dual-use risk before a model ships.

Responsibilities

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

What you should bring

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

Role signals

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.

Useful experience

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

Compensation and schedule

$20–$22 / hr
Expected arrangement: contractor , with program-defined task volume and review pacing. Placement depends on current program demand and reviewer confirmation.

Skills used in matching

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