For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
Anand Sagar

Anand Sagar

Software Engineer - Web and Mobile Development

INDIA flag
visakhapatnam, India
$25.00/hrIntermediateOtherInternal Proprietary Tooling

Key Skills

Software

Other
Internal/Proprietary Tooling

Top Subject Matter

No subject matter listed

Top Data Types

TextText

Top Label Types

RLHF
Computer Programming Coding
Prompt Response Writing SFT

Freelancer Overview

I am a software engineer with hands-on experience in building tools for AI training data collection, annotation, and evaluation. My work includes developing an RLHF (Reinforcement Learning from Human Feedback) rating tool that streamlines the process of comparing and evaluating AI model outputs using custom metrics like Tone, Accuracy, and Helpfulness, with efficient data export pipelines for seamless dataset creation. I have also engineered prompt optimization systems and code quality reviewers that automate evaluation, scoring, and iterative improvement of AI-generated content. My technical skills span JavaScript, Python, and modern web technologies, and I am proficient in designing intuitive UIs and automating data processing workflows. I am passionate about improving the quality and efficiency of AI data labeling and annotation processes through robust, user-friendly solutions.

IntermediateEnglishTeluguHindi

Labeling Experience

RLHF Data Evaluator & Tool Developer

OtherTextRLHFComputer Programming Coding
Designed and utilized a proprietary RLHF side-by-side evaluation workbench. Evaluated dual AI model outputs based on strict quality guidelines to generate training datasets. Scored responses across multiple granular metrics including conversational tone, factual accuracy, harmlessness, and helpfulness. Structured finalized evaluation ratings into JSON formats for direct integration into LLM fine-tuning pipelines. Maintained high quality and consistency across evaluations.

Designed and utilized a proprietary RLHF side-by-side evaluation workbench. Evaluated dual AI model outputs based on strict quality guidelines to generate training datasets. Scored responses across multiple granular metrics including conversational tone, factual accuracy, harmlessness, and helpfulness. Structured finalized evaluation ratings into JSON formats for direct integration into LLM fine-tuning pipelines. Maintained high quality and consistency across evaluations.

2025 - 2025

Education

G

Gayatri Vidya parishad college of engg

Electronics and communication engineering, visakhapatnam

Electronics and communication engineering
2023 - 2025

Work History

P

PromptForge

Software Engineer

Visakhapatnam
2023 - 2023
L

LLM Output Evaluator

Web Application Developer

Visakhapatnam
2022 - 2022