For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
Shruti Devganiya

Shruti Devganiya

AI Trainer (RLHF) | Python | Code Evaluation | Prompt Engineering | LLM Training

India flagSurat, India
$15.00/hrIntermediateScale AIRemotasksToloka

Key Skills

Software

Scale AIScale AI
RemotasksRemotasks
TolokaToloka
Label StudioLabel Studio
Google Cloud Vertex AIGoogle Cloud Vertex AI

Top Subject Matter

Artificial Intelligence – LLM Training & Evaluation
Software Development – Code Generation & Debugging
Data Science – NLP & Model Evaluation

Top Data Types

TextText
Computer Code ProgrammingComputer Code Programming

Top Task Types

RLHF
Evaluation Rating
Computer Programming Coding
Question Answering
Text Generation

Freelancer Overview

I am an IT student with strong proficiency in Python, C++, JavaScript (React, Node.js), and SQL, with a strong focus on specializing in debugging, optimizing, and evaluating code. I have experience analyzing AI-generated outputs, identifying logical errors, handling edge cases, and improving solution efficiency. I am particularly interested in RLHF-based AI training, where I contribute to ranking, correcting, and refining model-generated code and responses with clear technical reasoning. I am comfortable working on complex problem-solving tasks and explaining technical reasoning clearly for AI model improvement.

IntermediateEnglishHindi

Labeling Experience

AI Data Annotation & Code Evaluation (Practice)

Computer Code ProgrammingRLHF
Worked on AI training and data labeling tasks focused on evaluating and improving model-generated code in Python and JavaScript. Performed classification, ranking, and validation of AI outputs by identifying logical errors, optimizing performance, and ensuring proper handling of edge cases. Compared multiple responses and selected the most accurate and efficient solutions using structured reasoning, similar to RLHF workflows. Maintained high-quality standards by focusing on correctness, readability, and real-world applicability of generated code.

Worked on AI training and data labeling tasks focused on evaluating and improving model-generated code in Python and JavaScript. Performed classification, ranking, and validation of AI outputs by identifying logical errors, optimizing performance, and ensuring proper handling of edge cases. Compared multiple responses and selected the most accurate and efficient solutions using structured reasoning, similar to RLHF workflows. Maintained high-quality standards by focusing on correctness, readability, and real-world applicability of generated code.

2024 - Present

Education

V

Vanita Vishram Women's University

Bachelor of Science, Information Technology

Bachelor of Science
2023

Work History

J

J R Exim

Software Development & AI Evaluation

Surat
2025 - 2026
J

J R Exim

Computer Operator Intern

Surat
2025 - 2025