For employers

Hire this AI Trainer

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

Invite to Job
Umesh Dhivaria

Umesh Dhivaria

Software Development Engineer Intern

INDIA flag
New Delhi, India
$16.75/hrEntry LevelOtherInternal Proprietary Tooling

Key Skills

Software

Other
Internal/Proprietary Tooling

Top Subject Matter

Software Engineer - Buids production ready softwares
Frontend Developer - Builds Responsive UI interfaces
Prompt Engineer - Uses AI tools for best efficiency

Top Data Types

TextText
Computer Code ProgrammingComputer Code Programming

Top Task Types

Prompt Response Writing SFT
Computer Programming Coding
Evaluation Rating
Fine Tuning
RLHF
Text Generation

Freelancer Overview

Software Development Engineer Intern. Brings 1+ years of professional experience across complex professional workflows, research, and quality-focused execution. Education includes Bachelor of Technology, Delhi Technological University (2026) and High School Diploma, Yuvashakti Model School (2022).

Entry LevelHindiEnglish

Labeling Experience

Member of Managed workforces program

TextPrompt Response Writing SFT
I worked as an AI contributor on the Outlier platform, where my main responsibility was to help improve language models using Supervised Fine-Tuning and Reinforcement Learning from Human Feedback . In SFT tasks, I created high-quality responses to given prompts, making sure they were accurate, clear, well-structured, and easy to understand. I carefully followed the provided guidelines and refined answers by improving grammar, clarity, and overall presentation so the model could learn from ideal examples. In RLHF tasks, I evaluated multiple AI-generated responses, compared them based on accuracy, relevance, clarity, and usefulness, and ranked them accordingly. I also provided detailed feedback explaining why one response was better than others, helping the model understand quality differences. Throughout my work, I maintained strong attention to detail, followed strict quality standards, and ensured consistency in all tasks. This experience helped me strengthen my analytical thinking and communication skills while contributing to the development of more accurate and reliable AI systems.

I worked as an AI contributor on the Outlier platform, where my main responsibility was to help improve language models using Supervised Fine-Tuning and Reinforcement Learning from Human Feedback . In SFT tasks, I created high-quality responses to given prompts, making sure they were accurate, clear, well-structured, and easy to understand. I carefully followed the provided guidelines and refined answers by improving grammar, clarity, and overall presentation so the model could learn from ideal examples. In RLHF tasks, I evaluated multiple AI-generated responses, compared them based on accuracy, relevance, clarity, and usefulness, and ranked them accordingly. I also provided detailed feedback explaining why one response was better than others, helping the model understand quality differences. Throughout my work, I maintained strong attention to detail, followed strict quality standards, and ensured consistency in all tasks. This experience helped me strengthen my analytical thinking and communication skills while contributing to the development of more accurate and reliable AI systems.

2026 - Present

Member of India Managed Workforces

Computer Code ProgrammingRLHF
I worked as an AI contributor on the Outlier platform, where my main responsibility was to help improve language models using Supervised Fine Tuning and Reinforcement Learning from Human Feedback . In SFT tasks, I created high-quality responses to given prompts, making sure they were accurate, clear, well-structured, and easy to understand. I carefully followed the provided guidelines and refined answers by improving grammar, clarity, and overall presentation so the model could learn from ideal examples. In RLHF tasks, I evaluated multiple AI generated responses, compared them based on accuracy, relevance, clarity, and usefulness, and ranked them accordingly. I also provided detailed feedback explaining why one response was better than others, helping the model understand quality differences. Throughout my work, I maintained strong attention to detail, followed strict quality standards, and ensured consistency in all tasks. This experience helped me strengthen my analytical thinking and communication skills while contributing to the development of more accurate and reliable AI systems. Also , I have a experience of 3 years in c++ language

I worked as an AI contributor on the Outlier platform, where my main responsibility was to help improve language models using Supervised Fine Tuning and Reinforcement Learning from Human Feedback . In SFT tasks, I created high-quality responses to given prompts, making sure they were accurate, clear, well-structured, and easy to understand. I carefully followed the provided guidelines and refined answers by improving grammar, clarity, and overall presentation so the model could learn from ideal examples. In RLHF tasks, I evaluated multiple AI generated responses, compared them based on accuracy, relevance, clarity, and usefulness, and ranked them accordingly. I also provided detailed feedback explaining why one response was better than others, helping the model understand quality differences. Throughout my work, I maintained strong attention to detail, followed strict quality standards, and ensured consistency in all tasks. This experience helped me strengthen my analytical thinking and communication skills while contributing to the development of more accurate and reliable AI systems. Also , I have a experience of 3 years in c++ language

2026 - Present

Education

D

Delhi Technological University

Bachelor of Technology, Software Engineering

Bachelor of Technology
2022 - 2026
Y

Yuvashakti Model School

High School Diploma, Science

High School Diploma
2021 - 2022

Work History

B

Bramer

Software Development Engineer Intern

New Delhi
2025 - 2025