Harshit K.

Key Skills

Software

Other

Top Subject Matter

Financial Compliance & Risk Analysis

Investment Domain Expertise

Financial Analysis

Top Data Types

Text

Computer Code Programming

Document

Top Task Types

RLHF

Fine-tuning

Evaluation/Rating

Computer Programming/Coding

Classification

Freelancer Overview

RLHF Trainer and Evaluator for LLMs (Pareto.AI). Brings 8+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. AI-training focus includes data types such as Text and labeling workflows including RLHF.

Labeling Experience

RLHF Trainer and Evaluator for LLMs (Pareto.AI)

OtherTextRLHF

I conducted RLHF training and evaluation for large language models such as Claude and ChatGPT, focusing on finance and investment workflows. Responsibilities included reviewing outputs, testing model reasoning, and ensuring quality standards were met. Complex financial models were used as the context for annotating, scoring, and improving model performance. • Evaluated LLM outputs for logic gaps, hallucinations, and reasoning quality. • Designed and tested edge financial scenarios to enhance reliability. • Used Python and PowerShell to validate Code Interpreter outcomes for financial tasks. • Spent over 400 hours on annotation, evaluation, and workflow documentation.

2026 - 2026

Education

Work History