AI Safety Expert, English – Dutch

atMercorRemoteUS flagUnited StatesFreelanceArtificial IntelligenceMid-levelSenior$48 – $62/hour

Posted 5 hours ago

This is a fully remote position, open to applicants in United States.

πŸ“‹ Description

β€’ Engage in red team assessments of conversational AI models and agents.

β€’ Evaluate jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

β€’ Create human data by annotating failures, identifying vulnerabilities, and highlighting systemic risks.

β€’ Implement taxonomies, benchmarks, and playbooks to ensure consistent testing methodologies.

β€’ Generate reproducible reports, datasets, and actionable attack scenarios.

β€’ Identify vulnerabilities that automated testing may overlook.

β€’ Broaden evaluation coverage and mitigate unexpected production issues.

β€’ Enhance the safety and trustworthiness of customer AI systems.


⛳️ Requirements

β€’ Native proficiency in both English and Dutch.

β€’ Previous experience in red teaming within AI adversarial contexts, cybersecurity, or socio-technical probing.

β€’ Capability to investigate AI systems utilizing jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

β€’ Proficient in annotating failures, classifying vulnerabilities, and identifying systemic risks.

β€’ Ability to adhere to taxonomies, benchmarks, and playbooks.

β€’ Skilled in producing reproducible reports, datasets, and attack scenarios.

β€’ Competence in clearly communicating risks to both technical and non-technical stakeholders.

β€’ Flexibility to adapt across various projects and clients.

β€’ H1-B and STEM OPT candidates are not eligible.

β€’ Must be an independent contractor.


🏝️ Benefits

β€’ Work fully remotely.

β€’ Enjoy a flexible schedule.

β€’ Receive weekly payments through Stripe or Wise.

β€’ Competitive compensation.

β€’ Gain experience in human data-driven AI red teaming.

β€’ Collaborate with top researchers in the field.

β€’ Access wellness resources and clear protocols for higher-sensitivity projects.

β€’ Participation in higher-sensitivity projects is voluntary.

β€’ Reasonable accommodations available upon request.

β€’ Earn referral bonuses of up to $250 for each successful referral.

People also viewed

XenoPatch GmbH4 hours ago

AI Strategy – Digital Implementation

DE flagGermany OnlyPart-timeArtificial Intelligence
ApplyView job
Mercor4 hours ago

AI Safety Red Teamer

US flagUnited States OnlyFreelanceArtificial Intelligence$70 – $84/hour
ApplyView job
Mercor5 hours ago

AI Safety Expert, English – Dutch

US flagUnited States OnlyFreelanceArtificial Intelligence$48 – $62/hour
ApplyView job
Mercor5 hours ago

Marketing Expert – Paid Growth, AI Agent Environments

US flagUnited States OnlyFreelanceArtificial Intelligence$60 – $100/hour
ApplyView job
Mercor5 hours ago

AI Safety Red Teamer

US flagUnited States OnlyFreelanceArtificial Intelligence$70 – $84/hour
ApplyView job
Mercor5 hours ago

AI Safety Expert, English & Assamese

US flagUnited States OnlyFreelanceArtificial Intelligence$20 – $22/hour
ApplyView job

Never miss a great job!

Get handpicked remote jobs straight to your inbox weekly.

Trusted by 7,400+ designers