Sara G.

Key Skills

Software

Other

Top Subject Matter

AI model evaluation

hallucination detection and mitigation

and grading-guideline-based annotation for LLM outputs

Top Data Types

Text

Top Task Types

No task types listed

Freelancer Overview

AI Trainer at Airtm (AI evaluation and annotation of model responses using complex grading guidelines).. Core strengths include Other. AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

AI Trainer at Airtm (AI evaluation and annotation of model responses using complex grading guidelines).

OtherText

Provided AI model evaluations to assess response accuracy, grammar, safety, and helpfulness against expected grading criteria. Applied hallucination detection and mitigation techniques by reviewing outputs and flagging unreliable or unsafe content. Delivered actionable human feedback to improve model behavior and reduce errors over iterative reviews. • Evaluated more than 10 AI model responses • Assessed accuracy, grammar, safety, and helpfulness • Supported hallucination detection and mitigation workflows • Used detailed feedback to inform RLHF-style training improvements

Present

Education

Work History