Mandar B.

Key Skills

Software

Other

Top Subject Matter

Large language model (LLM) evaluation and training workflows

Top Data Types

Text

Image

Top Task Types

RLHF

Freelancer Overview

AI Freelancer (Remote) — RLHF-based response evaluation and ranking. Brings 4+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Engineering, N/A (2021). AI-training focus includes data types such as Text and labeling workflows including RLHF.

Labeling Experience

AI Freelancer (Remote) — RLHF-based response evaluation and ranking

OtherTextRLHF

Freelance AI work focused on RLHF-based evaluation by ranking and improving AI-generated text outputs against user intent and quality criteria. The labeling activity included structured comparisons and scoring based on relevance, factual accuracy, tone, and alignment. Work was performed using iterative feedback cycles to enhance model accuracy and reliability. • Rated and ranked AI responses for quality and relevance • Evaluated factual accuracy and tone relative to instructions • Compared multi-model outputs for consistency and improvement • Applied RLHF-inspired ranking and feedback loops

2024 - Present

Education

Work History