Radin M.

Key Skills

Software

Don't disclose

Top Subject Matter

Machine learning datasets (classification/prediction/recommendation) and LLM-related evaluation

LLM evaluation pipelines and AI performance regression detection

Top Data Types

Text

Top Task Types

Fine-tuning

Freelancer Overview

Freelance Full Stack Engineer (AI-powered features, ML solutions, and labeled dataset preparation). Brings 5+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Don't disclose. Education includes Bachelor of Arts, York University (2026). AI-training focus includes data types such as Text, Computer Code, and Programming and labeling workflows including Fine-tuning, Evaluation, and Rating.

Labeling Experience

Freelance Full Stack Engineer (offline evaluation pipelines and performance feedback)

Don't disclose

Implemented offline evaluation pipelines and feedback systems to assess model performance and identify regressions during iteration. Designed evaluation workflows and measurement processes to validate changes to AI systems, including LLM integrations. Used automated evaluation tooling to track quality and stability across releases. • Built offline evaluation pipelines for model assessment • Implemented feedback systems to detect regressions • Automated performance metrics for iterative improvements • Supported LLM integration evaluation workflows

2022 - Present

Freelance Full Stack Engineer (AI-powered features, ML solutions, and labeled dataset preparation)

Don't discloseTextFine-tuning

Prepared, cleaned, and labeled datasets for machine learning projects to support model training, evaluation, and fine-tuning. Worked on classification, prediction, and recommendation tasks using labeled data to improve model performance. Built dataset assets and evaluation artifacts used in offline experimentation pipelines. • Dataset preparation and labeling for AI/ML training • Cleaned and curated data for evaluation and fine-tuning • Supported model performance optimization using labeled datasets • Prepared inputs for offline evaluation and feedback workflows

2022 - Present

Education

Work History