- Erfahrung
- Beliebig
- Gehalt
- 20 – 22 USD/Stunde
- Stellenangebote
- 1
- Veröffentlicht
- vor 3 Wochen
- Arbeitsmodus
- Arbeiten von zu Hause
- Teilnahmeberechtigung
- Candidates who are fluent in both English and Urdu and have experience in AI red teaming, adversarial work, cybersecurity, or related socio-technical risk analysis can apply.
- Wieder aufnehmen
- Bewerbung erforderlich
Stellenbeschreibung
About the Role
This opportunity is with a company that connects highly skilled creative and technical professionals with major AI research organizations. The team is based in San Francisco and is backed by well-known investors including Benchmark, General Catalyst, Peter Thiel, Adam D'Angelo, Larry Summers, and Jack Dorsey.
Role Overview
The position is for AI Safety Experts working in English and Urdu. This is a remote contract role focused on evaluating conversational AI systems and agents for weaknesses, unsafe behaviors, and misuse risks.
Compensation
Pay is set at $20 to $22 per hour.
Key Work Areas
- Test conversational AI models and agents to uncover jailbreaks, prompt injection issues, and other misuse scenarios.
- Produce structured human-annotated data by identifying failures, labeling vulnerabilities, and highlighting broader risk patterns.
- Use defined taxonomies, benchmarks, and testing playbooks to keep evaluations consistent and repeatable.
- Create clear, reproducible documentation so findings can be turned into reports, datasets, and adversarial examples.
- Assess AI responses on sensitive areas such as bias and misinformation, with the option to contribute to more sensitive projects.
Required Qualifications
- Fluency at a native level in both English and Urdu.
- Previous experience with red teaming, AI adversarial testing, cybersecurity, or socio-technical probing.
- Strong ability to communicate risks in a way that works for both technical and non-technical audiences.
Preferred Background
- Experience in adversarial machine learning, cybersecurity, or socio-technical risk assessment.
- Creative probing abilities such as psychology, acting, or writing that support unconventional adversarial thinking.
Application Steps
The application takes about 20 to 30 minutes and includes three steps: uploading a resume, completing an AI interview based on the resume, and submitting the form.
Support Information
If you need help during the process, support is available through the company’s help channel listed in the application materials.
Additional Note
The review team checks applications every day, so candidates should complete all steps to be considered.