Adarsh Y.

Key Skills

Software

Scale AI

Don't disclose

Top Subject Matter

Large language model (LLM) training and evaluation

Legal Services & Contract Review

Regulatory Compliance & Risk Analysis

Top Data Types

Computer Code Programming

Text

Document

Top Task Types

Fine-tuning

Evaluation/Rating

Computer Programming/Coding

Prompt + Response Writing (SFT)

Freelancer Overview

Advanced AI Training Coder (Remote, Freelance) at Outlier.ai. 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 Technology, Loknayak Jai Prakash Institute of Technology (2023) and Generative AI Professional Certificate, IBM (2025). AI-training focus includes data types such as Text and labeling workflows including Evaluation and Rating.

Labeling Experience

Advanced AI Training Coder (Remote, Freelance) at Outlier.ai

Don't discloseText

Provided AI training by evaluating and refining AI-generated code and text responses to ensure accuracy, logical coherence, and compliance with predefined quality guidelines. Analyzed complex prompts and model outputs to identify performance gaps and improve the model’s contextual understanding and code correctness. Delivered structured feedback at scale to support continuous improvement of LLM training pipelines and AI model evaluation workflows. • Reviewed model outputs against quality rubrics and expected behaviors. • Assessed response quality across multiple technical domains. • Provided corrective guidance to improve LLM reasoning and generation. • Collaborated within a distributed remote team for iterative evaluation cycles.

2024 - 2026

AI Response Fine-Tuning & Frontend Enhancement for LLM-Generated Code

Scale AIComputer Code ProgrammingFine-tuningEvaluation/Rating

Worked as an AI Trainer and Response Fine-Tuner focused on improving Large Language Model (LLM) outputs for frontend web development tasks. The project involved evaluating model-generated responses based on given prompts and enhancing them while strictly maintaining prompt requirements.

2025 - 2025

Education

Work History