For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
O

Omid Torkan

AI & Machine Learning Engineer (Freelance) – LLM RLHF Evaluation/Data Labeling

Italy flagRome, Italy
$20.00/hrExpertOther

Key Skills

Software

Other

Top Subject Matter

Large Language Models
Natural Language Processing
Model Evaluation

Top Data Types

TextText
AudioAudio
DocumentDocument

Top Task Types

RLHFRLHF
ClassificationClassification

Freelancer Overview

AI & Machine Learning Engineer (Freelance) – LLM RLHF Evaluation/Data Labeling. Brings 12+ years of professional experience across legal operations, contract review, compliance, and structured analysis. Core strengths include Internal, Proprietary Tooling, and Other. Education includes Master of Science, University of Milan (2024) and Bachelor of Science, Azad University (2012). AI-training focus includes data types such as Text and labeling workflows including RLHF and Classification.

ExpertEnglish

Labeling Experience

AI & Machine Learning Engineer (Freelance) – LLM RLHF Evaluation/Data Labeling

TextRLHF
Evaluated and enhanced outputs of Large Language Models (LLMs) using RLHF techniques. Designed and refined prompts to optimize AI-generated text for quality and accuracy. Provided structured feedback and analysis to improve model performance and consistency. • Applied iterative feedback loops to address model inaccuracies. • Collaborated in cross-functional teams for continuous model improvement. • Focused on optimizing prompt engineering workflows for LLMs. • Used internal/proprietary tooling for evaluation and data tracking.

Evaluated and enhanced outputs of Large Language Models (LLMs) using RLHF techniques. Designed and refined prompts to optimize AI-generated text for quality and accuracy. Provided structured feedback and analysis to improve model performance and consistency. • Applied iterative feedback loops to address model inaccuracies. • Collaborated in cross-functional teams for continuous model improvement. • Focused on optimizing prompt engineering workflows for LLMs. • Used internal/proprietary tooling for evaluation and data tracking.

2025 - Present

AI & Data Science Intern – Toxicology Data Classification & XAI

OtherTextClassification
Developed and trained AI-powered models for chemical toxicity and risk assessment using labeled datasets. Implemented AI interpretability techniques to ensure regulatory alignment and transparency. Queried and processed toxicological data via specialized APIs to support safety evaluations. • Used OpenTox APIs for data retrieval and labeling workflows. • Applied machine learning and deep learning for predictive toxicology. • Contributed to open data initiatives in toxicology research. • Employed SHAP and LIME for model explanation tasks.

Developed and trained AI-powered models for chemical toxicity and risk assessment using labeled datasets. Implemented AI interpretability techniques to ensure regulatory alignment and transparency. Queried and processed toxicological data via specialized APIs to support safety evaluations. • Used OpenTox APIs for data retrieval and labeling workflows. • Applied machine learning and deep learning for predictive toxicology. • Contributed to open data initiatives in toxicology research. • Employed SHAP and LIME for model explanation tasks.

2025 - 2025

Data Scientist (Thesis Project) – Text Labeling for Sentiment Analysis

OtherTextClassification
Labeled and classified text datasets for sentiment analysis and neural network training in an academic research project. Processed and annotated natural language data to improve the interpretability and performance of RNN models. Developed workflows integrating Python-based interpretability techniques for transparent AI outcomes. • Implemented data annotation and preprocessing for sentiment tasks. • Evaluated model outputs to fine-tune labeling criteria. • Built statistical language models for NLP experimentation. • Used Jupyter, scikit-learn, and Python tools for workflow automation.

Labeled and classified text datasets for sentiment analysis and neural network training in an academic research project. Processed and annotated natural language data to improve the interpretability and performance of RNN models. Developed workflows integrating Python-based interpretability techniques for transparent AI outcomes. • Implemented data annotation and preprocessing for sentiment tasks. • Evaluated model outputs to fine-tune labeling criteria. • Built statistical language models for NLP experimentation. • Used Jupyter, scikit-learn, and Python tools for workflow automation.

2024 - 2024

Education

U

University of Milan

Master of Science, Computer Science

Master of Science
2024 - 2024
A

Azad University

Bachelor of Science, Software Engineering

Bachelor of Science
2012 - 2012

Work History

O

OutlierAI

AI & Machine Learning Engineer

Rome
2025 - Present
O

OpenTox

AI & Data Science Intern

Basel
2025 - 2025