AI Safety Expert, English – Dutch

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

Posted Sep 7

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

📋 Description

• Engage in red team assessments of conversational AI models and agents.

• Evaluate jailbreaks, prompt injections, misuse scenarios, bias exploitation, and multi-turn manipulations.

• Create human data by annotating failures, identifying vulnerabilities, and highlighting systemic risks.

• Implement taxonomies, benchmarks, and playbooks to ensure consistent testing methodologies.

• Generate reproducible reports, datasets, and actionable attack scenarios.

• Identify vulnerabilities that automated testing may overlook.

• Broaden evaluation coverage and mitigate unexpected production issues.

• Enhance the safety and trustworthiness of customer AI systems.


⛳️ Requirements

• Native proficiency in both English and Dutch.

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

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

• Proficient in annotating failures, classifying vulnerabilities, and identifying systemic risks.

• Ability to adhere to taxonomies, benchmarks, and playbooks.

• Skilled in producing reproducible reports, datasets, and attack scenarios.

• Competence in clearly communicating risks to both technical and non-technical stakeholders.

• Flexibility to adapt across various projects and clients.

• H1-B and STEM OPT candidates are not eligible.

• Must be an independent contractor.


🏝️ Benefits

• Work fully remotely.

• Enjoy a flexible schedule.

• Receive weekly payments through Stripe or Wise.

• Competitive compensation.

• Gain experience in human data-driven AI red teaming.

• Collaborate with top researchers in the field.

• Access wellness resources and clear protocols for higher-sensitivity projects.

• Participation in higher-sensitivity projects is voluntary.

• Reasonable accommodations available upon request.

• Earn referral bonuses of up to $250 for each successful referral.

People also viewed

Mindrift1 day ago

Physician, Medical AI Evaluation

US flagAlabama, +5 more statesPart-timeArtificial Intelligence$100/hour
ApplyView job
Mindrift1 day ago

Physician Reviewer, MD/DO – Medical AI Evaluation

RO flagRomania, +5 more countriesPart-timeArtificial Intelligence$60/hour
ApplyView job
ClickHouse1 day ago

AI Operations Engineer

US flagUnited States OnlyFull-timeArtificial Intelligence$110k – $165k/year
ApplyView job
1mind1 day ago

AI Conversation Designer

US flagUnited States OnlyFull-timeArtificial Intelligence$100k – $150k/year
ApplyView job
Tucuvi1 day ago

Conversation AI Manager

ES flagSpain OnlyFull-timeArtificial Intelligence
ApplyView job
Human Agency1 day ago

Director – AI Transformation

US flagUnited States, +1 more countryFull-timeArtificial Intelligence
ApplyView job

Never miss a great job!

Get handpicked remote jobs straight to your inbox weekly.

Trusted by 7,400+ designers