Atticus F.

Key Skills

Software

Don't disclose

Scale AI

Labelbox

Micro1

Top Subject Matter

Reinforcement Learning from Human Feedback (RLHF)

model evaluation

and safety/red-teaming style prompt testing

Top Data Types

Text

Image

Video

Top Task Types

RLHF

Classification

Fine-tuning

Red Teaming

Transcription

Evaluation/Rating

Data Collection

Segmentation

Bounding Box

Freelancer Overview

AI Tutor — high-complexity RLHF and SFT data/training evaluation for multimodal models. Brings 3+ years of professional experience across complex professional workflows, research, and quality-focused execution. Previously worked for xAI and Scale AI. Education includes Bachelor of Science, SWPS University (2026) and Associate of Science, Aiken Technical College (2020). AI-training focus includes data types such as Text and labeling workflows including RLHF, Evaluation, and Rating.

Labeling Experience

AI Tutor — high-complexity RLHF and SFT data/training evaluation for multimodal models

Don't discloseTextRLHF

Served as an AI Tutor performing RLHF and SFT-oriented evaluation and training support for high-complexity tasks. Assessed generations for prompt adherence, factual accuracy, and overall response quality to maintain performance standards. Applied adversarial prompting strategies to surface model biases and vulnerabilities, including social engineering and prompt injection risks. • Evaluated prompt adherence and response quality. • Checked factual accuracy against expected behavior. • Produced and reviewed multimodal training inputs across multiple modalities. • Created adversarial prompts using psychological principles to test robustness.

2025 - 2026

AI Language Analyst — multimodal reasoning optimization and fact-checking verification

Scale AIText

Worked as an AI Language Analyst producing quality-checked annotations and evaluation for multimodal and fact-checking projects. Verified model outputs against academic sources while maintaining a consistent quality benchmark through ongoing review. Contributed to rubric creation and comparative analysis to improve multimodal model reasoning performance. • Performed fact verification by comparing outputs to academic sources. • Maintained a 95% quality benchmark on reviewed outputs. • Authored rubrics and used comparative evaluations for reasoning. • Supported multimodal project review as a promoted reviewer.

2023 - 2025

Education

Work History