For employers

Hire this AI Trainer

Sign in or create an account to invite AI Trainers to your job.

LoginCreate account
Invite to Job
A
Anup Gajurel

Anup Gajurel

AI Data Labeling & RLHF Contributor

Nepal flagDamak, Nepal
$15.00/hrIntermediateOther

Key Skills

Software

Other

Top Subject Matter

Physics Domain Expertise
Mathematics Domain Expertise
Programming Domain Expertise

Top Data Types

TextText
VideoVideo

Top Task Types

RLHFRLHF
Prompt + Response Writing (SFT)Prompt + Response Writing (SFT)

Freelancer Overview

AI Data Labeling & RLHF Contributor. Brings 3+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes High School Diploma, Damak Adarsha Boarding School (2024). AI-training focus includes data types such as Text and labeling workflows including RLHF, Prompt + Response Writing (SFT), and Evaluation.

IntermediateEnglish

Labeling Experience

LLM Evaluation/Preference Ranking Rater

OtherText
Performed evaluation and preference ranking tasks for language model outputs within the context of science and math education content. Compared AI-generated text against rubrics for logical accuracy, domain fidelity, and academic rigor. Provided human feedback to refine model selection and improve response generation quality. • Used comparative rating to improve model performance for scientific tasks. • Assessed clarity, correctness, and completeness of AI-generated solutions. • Evaluated and scored outputs for LLMs working on physics and math questions. • Documented evaluation results to support ongoing model improvement cycles.

Performed evaluation and preference ranking tasks for language model outputs within the context of science and math education content. Compared AI-generated text against rubrics for logical accuracy, domain fidelity, and academic rigor. Provided human feedback to refine model selection and improve response generation quality. • Used comparative rating to improve model performance for scientific tasks. • Assessed clarity, correctness, and completeness of AI-generated solutions. • Evaluated and scored outputs for LLMs working on physics and math questions. • Documented evaluation results to support ongoing model improvement cycles.

2024 - Present

AI Training Prompt & Response Annotator

OtherTextPrompt Response Writing SFT
Created and annotated structured prompts and corresponding high-quality responses for supervised fine-tuning of AI and LLM models. Focused primarily on mathematics, physics, and scientific inquiry subjects to enhance reasoning ability in generative models. Contributed to structured data annotation and formatting for both English and Nepali content. • Wrote and reviewed prompt-response pairs for AI model fine-tuning. • Standardized problem formats and detailed academic solutions. • Labeled responses for scientific correctness and clarity. • Adapted prompts to diverse scientific and mathematical contexts.

Created and annotated structured prompts and corresponding high-quality responses for supervised fine-tuning of AI and LLM models. Focused primarily on mathematics, physics, and scientific inquiry subjects to enhance reasoning ability in generative models. Contributed to structured data annotation and formatting for both English and Nepali content. • Wrote and reviewed prompt-response pairs for AI model fine-tuning. • Standardized problem formats and detailed academic solutions. • Labeled responses for scientific correctness and clarity. • Adapted prompts to diverse scientific and mathematical contexts.

2024 - Present

AI Data Labeling & RLHF Contributor

OtherTextRLHF
Worked on AI training tasks involving reinforcement learning from human feedback (RLHF) in physics, mathematics, and programming domains. Created, rated, and analyzed responses for large language model prompt-completion pairs to improve model accuracy and reliability. Performed preference ranking, fact-checking, and prompt engineering for scientific questions and reasoning tasks. • Labeled and evaluated data for LLMs in scientific and quantitative subjects. • Participated in prompt development and response evaluation tasks. • Generated high-quality training and evaluation datasets for AI models. • Collaborated in red teaming and RLHF projects in English and Nepali.

Worked on AI training tasks involving reinforcement learning from human feedback (RLHF) in physics, mathematics, and programming domains. Created, rated, and analyzed responses for large language model prompt-completion pairs to improve model accuracy and reliability. Performed preference ranking, fact-checking, and prompt engineering for scientific questions and reasoning tasks. • Labeled and evaluated data for LLMs in scientific and quantitative subjects. • Participated in prompt development and response evaluation tasks. • Generated high-quality training and evaluation datasets for AI models. • Collaborated in red teaming and RLHF projects in English and Nepali.

2024 - Present

Education

D

Damak Adarsha Boarding School

High School Diploma, Physics, Chemistry, Mathematics, Computer Science

High School Diploma
2024

Work History

S

S-I Brand

Co-Founder & Content Developer

Damak
2024 - Present