LLM Evaluator – Model Response Analyst

About the role

We are looking for a detail‑oriented LLM Evaluator to assess and improve the performance of large language models. Working remotely with a global team, you will analyze AI‑generated content for accuracy, coherence, safety, bias, and alignment with our guidelines.

Key responsibilities

• Evaluate and rank model‑generated text using complex rubrics covering factuality, coherence, safety, instruction‑following, and creativity.
• Compare multiple model responses to the same prompt and justify the preferred output.
• Provide concise feedback to modeling and training teams about recurring failure patterns.
• Craft adversarial prompts to expose biased, harmful, or insecure model behavior.
• Collaborate with QA to refine evaluation guidelines and handle ambiguous edge cases.
• Participate in cross‑checking sessions to calibrate scoring standards and ensure inter‑rater reliability.
• Investigate underperforming outputs, hypothesize root causes, and flag novel behaviors for research.

Required profile

• Minimum 2 years of professional experience in computational linguistics, data analysis, technical writing, NLP/AI quality assurance, or cognitive science.
• Bachelor’s degree in Computer Science or a related field.
• Strong understanding of prompt engineering and ability to explain why a model output is good or bad.
• Experience with Reinforcement Learning from Human Feedback (RLHF) data collection.
• Proven track record of maintaining consistency across evaluation teams and conducting calibration sessions.
• Familiarity with dataset sourcing, cleaning, annotation, and the impact of data distribution on model performance.
• Knowledge of A/B testing concepts and experiment design for model comparisons.

Required skills

• Prompt engineering
• RLHF data collection
• Dataset annotation
• Data cleaning
• A/B testing
• Experiment design
• Evaluation rubric development

What we offer

• Fully remote work with flexible hours
• Opportunity to influence cutting‑edge AI research
• Collaboration with an international, multidisciplinary team