Full Description

Position: AI Red-Teamer — Adversarial AI Testing (Advanced) | English & Italian

Type: Hourly contract

Compensation: $50.5/hour

Location: Remote

Commitment: 10–40 hours/week

Role Responsibilities

Perform adversarial testing on conversational AI systems through jailbreaks, prompt injections, misuse cases, and multi-turn manipulation. Identify and document model vulnerabilities related to bias, misinformation, unsafe behavior, and systemic risk. Generate high-quality human data by annotating failures, classifying attack types, and flagging risk patterns. Follow structured taxonomies, benchmarks, and testing playbooks to ensure consistent evaluation coverage. Produce reproducible artifacts such as reports, datasets, and documented attack cases for customers and research teams. Communicate findings clearly to both technical and non-technical stakeholders.

Requirements

Native-level fluency in both English and Italian. Prior experience in red teaming, adversarial AI testing, cybersecurity, or socio-technical risk evaluation. Strong ability to think creatively and intentionally push systems toward failure points. Structured approach to testing using frameworks, benchmarks, and repeatable methodologies. Excellent written communication skills with strong documentation discipline. Ability to work independently and adapt across different customers and project scopes. Comfortable reviewing AI outputs that may involve sensitive topics (optional participation in higher-sensitivity work).

Application Process (Takes 20 Min)

Upload resume Interview (15 min) Submit form