Adarsh J.

Key Skills

Software

Scale AI

Remotasks

Label Studio

Argilla

Top Subject Matter

Software Engineering & Technical AI Alignment (RLHF/SFT)

Natural Language Processing & Information Retrieval (RAG)

Advanced Machine Learning & Theoretical Data Science

Top Data Types

Computer Code Programming

Top Task Types

Question Answering

RLHF

Fine-tuning

Evaluation/Rating

Freelancer Overview

Experienced AI Training Specialist with a proven track record of generating high-quality datasets for next-generation Large Language Models (LLMs). Having completed $100+ worth of technical tasks on Scale AI/Outlier, I specialize in Reinforcement Learning from Human Feedback (RLHF) and Supervised Fine-Tuning (SFT) for coding and reasoning models. My background includes a Software Development Internship focusing on Semantic RAG systems and selection into the prestigious Amazon ML Summer School, allowing me to provide high-signal technical feedback that adheres to strict safety, truthfulness, and performance guidelines.

Labeling Experience

Technical AI Training Specialist (Freelance) — Outlier/Scale AI

Computer Code ProgrammingRLHF

Technical Data Specialist and RLHF Contributor within the Scale AI/Outlier ecosystem, specializing in SFT and Reinforcement Learning from Human Feedback for Tier-3 coding and reasoning models. Developed high-signal datasets through complex prompt engineering, multi-turn adversarial testing, and ground-truth generation. Consistently maintained a 4.5/5.0 quality rating while performing rigorous code debugging (Python) and logical reasoning evaluations. Executed $100+ in technical tasking, ensuring strict adherence to HHH (Helpfulness, Honesty, Harmlessness) safety alignment and factuality protocols for major LLM deployments.

2026 - 2026

Education

Work History