Mohit D.

Key Skills

Software

Don't disclose

Top Subject Matter

Mathematical reasoning and LLM evaluation (arithmetic, algebra, calculus)

LLM output quality assessment

RLHF feedback

Top Data Types

Text

Top Task Types

RLHF

Freelancer Overview

ML Model Evaluation & Prompt Testing / LLM Prompting & Response Annotation. Brings 1+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include OpenAI API and Don't disclose. Education includes Bachelor of Technology, Punjab Engineering College (Deemed to be University) (2026) and Higher Secondary Certificate, Senior Secondary School, Punjab (2022). AI-training focus includes data types such as Text and labeling workflows including Evaluation, Rating, and RLHF.

Labeling Experience

AI Trainer Skills: data labeling, quality rating, RLHF feedback

Don't discloseTextRLHF

Conducted data labeling, cleaning, and RLHF-style feedback generation by reviewing model outputs and providing quality ratings. Performed critical evaluation of LLM logical consistency to create reliable supervision signals. Reviewed multilingual content to ensure annotation quality across English and Hindi inputs. • Labeled and cleaned data for training readiness • Provided RLHF feedback based on output quality • Evaluated logical consistency of LLM responses • Performed multilingual content review (English & Hindi)

2022 - Present

ML Model Evaluation & Prompt Testing / LLM Prompting & Response Annotation

Text

Designed a structured pipeline to benchmark LLM responses across mathematical reasoning tasks and annotate outputs for training and evaluation purposes. Applied correctness labeling and reasoning quality scoring to capture logical consistency and accuracy for downstream model improvement. Performed step-by-step feedback simulation to support AI training workflow development and iterate on prompt and response quality. • Annotated model outputs with correctness labels • Assigned reasoning quality scores for consistency checks • Benchmarked arithmetic, algebra, calculus reasoning responses • Simulated real AI training feedback loops

2022 - 2026

Education

Work History