Flavia Corso

Key Skills

Software

Mercor

Top Subject Matter

AI Safety

Model Alignment

AI Training

Top Data Types

Text

Document

Top Task Types

RLHF

Freelancer Overview

AI Safety Expert, Reviewer and SFT Annotator. Brings 11+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Mercor and Alignerr. Education includes Second Level Master Degree, Università degli Studi di Genova (2019) and Master of Arts, Università degli Studi di Torino (2014). AI-training focus includes data types such as Text and labeling workflows including RLHF, Evaluation, and Rating.

Labeling Experience

AI Safety Expert, Reviewer and SFT Annotator

MercorTextRLHF

As an AI Safety Expert, Reviewer, and SFT Annotator at Mercor, I evaluated and annotated training data for reinforcement learning from human feedback (RLHF) purposes. My responsibilities included reviewing AI-generated outputs and providing feedback to ensure alignment, safety, and high-quality model behavior. The work focused on performance evaluation and accurate annotation to support fine-tuning of large language models. • Conducted performance reviews of AI outputs for safety and quality. • Evaluated and annotated text data for RLHF training. • Focused on model alignment and bias mitigation. • Used internal or proprietary tooling for annotation and review tasks.

As an AI Safety Expert, Reviewer, and SFT Annotator at Mercor, I evaluated and annotated training data for reinforcement learning from human feedback (RLHF) purposes. My responsibilities included reviewing AI-generated outputs and providing feedback to ensure alignment, safety, and high-quality model behavior. The work focused on performance evaluation and accurate annotation to support fine-tuning of large language models. • Conducted performance reviews of AI outputs for safety and quality. • Evaluated and annotated text data for RLHF training. • Focused on model alignment and bias mitigation. • Used internal or proprietary tooling for annotation and review tasks.

2026 - Present

AI Trainer & Model Evaluator

Text

In the role of AI Trainer & Model Evaluator, I trained and refined AI models focusing on the evaluation of model performance. My tasks included assessing AI outputs for quality and accuracy, as well as providing feedback for further model improvement. The emphasis was on ensuring the delivery of high-quality, reliable AI products through continuous model evaluation. • Evaluated and reviewed text outputs from large language models. • Provided detailed feedback to improve model results. • Supported ongoing refinement and fine-tuning initiatives. • Used internal evaluation tools or software related to Alignerr.

In the role of AI Trainer & Model Evaluator, I trained and refined AI models focusing on the evaluation of model performance. My tasks included assessing AI outputs for quality and accuracy, as well as providing feedback for further model improvement. The emphasis was on ensuring the delivery of high-quality, reliable AI products through continuous model evaluation. • Evaluated and reviewed text outputs from large language models. • Provided detailed feedback to improve model results. • Supported ongoing refinement and fine-tuning initiatives. • Used internal evaluation tools or software related to Alignerr.

2024 - Present

Education

Work History