Crossing Hurdles
Website:
crossinghurdles.com
Job details:
Position: LLM – AI Quality Analyst (Personalization) – Danish
Type: Short-Term Contract
Location: Remote
Commitment: Part-time (20–40 hours/week, 4-hour overlap with PST)
Engagement Length: 1 month
Start Date: Immediate
Role Responsibilities
- Evaluate AI personalization quality across multi-turn conversational scenarios
- Design prompts based on personal context to test AI personalization capabilities
- Assess model responses for grounding, integration, and overall helpfulness
- Perform side-by-side (SxS) evaluation of AI outputs and rank response quality
- Identify issues such as hallucinations, incorrect personalization, and weak inference
- Write clear, structured rationales for evaluation decisions
- Extract and verify system debug information for accuracy of personalization
- Maintain data hygiene by managing and clearing evaluation histories
Requirements
- Strong proficiency in Danish (reading and writing)
- Ability to evaluate nuanced AI responses with strong analytical thinking
- Experience in AI quality evaluation, data annotation, content moderation, or similar analytical work
- Strong understanding of personalization concepts and evaluation frameworks
- Ability to design creative, multi-turn prompts for testing AI systems
- Excellent written communication skills for structured feedback and reasoning
- Comfortable using a personal Google account with enabled data sources for evaluation
- Self-driven and able to work independently in a remote environment
Application Process
- Fill out the application form
- Complete the ICF
- Assessment (includes screener and language vetting)
Click on Apply to know more.