Multilingual AI Safety Evaluation Specialist

IXO is engaging specialists to evaluate AI safety behavior in English and another language you understand at native level. Your contribution is technical work: make the reasoning inspectable, identify substantive errors and provide evidence that supports a reliable assessment.

Work you will do

• Construct and assess language-specific prompts and multi-turn interactions that probe model safety behavior.
• Identify harmful, misleading or culturally inappropriate responses and explain the linguistic context behind the finding.
• Record the failure mode and a clear assessment rationale; apply the experience requirements of the language track for which you are eligible.

Required background and routes

• Native-level ability in the specified language alongside fluent English, with precise judgment about meaning, completeness, appropriateness and risk. Apply guidelines consistently and explain subtle problems clearly.
• For Norwegian, Danish, Finnish, Swedish, Thai, Portuguese, Indonesian, Vietnamese, Dutch and Malay tracks, prior red-team work is required. That additional requirement does not apply to the Urdu, Kannada, Tamil, Telugu, Malayalam, Punjabi, Assamese, Gujarati, Odia, Bengali or Marathi tracks.
• The Portuguese track concerns non-Brazilian Portuguese. Language eligibility is confirmed for the selected track before assignment.

Preferred background

• Adversarial ML, prompt-injection or alignment testing; penetration testing/reverse engineering; misinformation or abuse analysis; or creative probing informed by writing, acting or psychology.

Deliverables

• Submit the completed technical artifact or assessment with its supporting evidence, explicit assumptions, reproducible checks where applicable, and concise reasons for each material judgment.
• Address review findings within the agreed scope.

Location and schedule

Remote assignments are scheduled by agreement, with no guaranteed weekly volume. Availability planning can include 40 hours per week depending on the track. IXO confirms the applicable timing before work.

Pay and working terms

$53 $67/hr USD. The agreed hourly rate, scope, schedule and acceptance criteria are confirmed before work starts. Applying does not guarantee an assignment. Use public, licensed or otherwise authorized material only; do not submit confidential employer information, personal data or restricted research.