Andrei

Key Skills

Software

Scale AI

Top Subject Matter

Large Language Model (LLM) prompt-response evaluation

Stem Domain Expertise

Italian-language content

Top Data Types

Text

Document

Top Task Types

RLHF

Freelancer Overview

AI Training Contributor — Outlier (Scale AI). Brings 5+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Scale AI. Education includes High School Diploma, ITTS – Volta (2022). AI-training focus includes data types such as Text and labeling workflows including RLHF. Bilingual (Italian/English) technical professional with 2+ years of hands-on experience in AI training and software-related quality assurance at Outlier (Scale AI). Strong foundation in electrical engineering combined with practical exposure to software development workflows, AI/LLM evaluation, prompt engineering, and code-related annotation tasks. Detail-oriented problem solver passionate about technology, automation, and improving software systems through data-driven feedback.

Labeling Experience

AI Training Contributor — Outlier (Scale AI)

Scale AITextRLHF

As an AI Training Contributor at Outlier (Scale AI), I crafted and evaluated large volumes of training data for language models. I designed adversarial prompts and reviewed model responses, focusing on error identification and nuanced feedback for AI improvement. My tasks included rubric-based scoring, ranking, and providing direct fine-tuning input for LLMs. • Authored, reviewed, and ranked thousands of AI-generated model responses to improve reasoning quality. • Designed adversarial prompts to surface hallucinations, unsafe outputs, and model weaknesses. • Applied detailed rubrics to evaluate responses for correctness, tone, and coherence. • Provided structured written feedback directly used in AI fine-tuning pipelines.

As an AI Training Contributor at Outlier (Scale AI), I crafted and evaluated large volumes of training data for language models. I designed adversarial prompts and reviewed model responses, focusing on error identification and nuanced feedback for AI improvement. My tasks included rubric-based scoring, ranking, and providing direct fine-tuning input for LLMs. • Authored, reviewed, and ranked thousands of AI-generated model responses to improve reasoning quality. • Designed adversarial prompts to surface hallucinations, unsafe outputs, and model weaknesses. • Applied detailed rubrics to evaluate responses for correctness, tone, and coherence. • Provided structured written feedback directly used in AI fine-tuning pipelines.

2024 - Present

Education

Work History