For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
Bipanjot Dhillon

Bipanjot Dhillon

LLM Prompt Evaluator & AI Data Labeler – Chatbot Feedback, Text & UX

Canada flagBrampton, Canada
$18.00/hrIntermediateOther

Key Skills

Software

Other

Top Subject Matter

No subject matter listed

Top Data Types

Computer Code ProgrammingComputer Code Programming
ImageImage
TextText

Top Task Types

Computer Programming Coding
Data Collection
Prompt Response Writing SFT
Text Generation
Text Summarization

Freelancer Overview

I specialize in AI training and data labelling with a focus on text generation, prompt evaluation, and conversational UX. I’ve contributed to projects involving GPT model response ranking, usability scoring, and chatbot refinement. My experience includes building SmartCity-style chatbots that answer real-time civic queries and testing prompt quality for AI blog content and user interactions. I’m comfortable with tools like OpenAI Playground, Google Forms, and image/text feedback systems. I bring strong attention to detail, fast task adaptation, and a solid foundation in large language model behaviour.

IntermediateUrduHindiFrenchEnglishPunjabi

Labeling Experience

AI Blog Prompt Testing – LLM Output Review & Refinement

OtherTextText GenerationEvaluation Rating
Designed and tested prompt structures for AI-generated blog content using GPT-4 and Gemini. Evaluated the accuracy, tone, and relevance of model responses. Scored and ranked multiple outputs for consistency, clarity, and engagement. Provided feedback to improve AI-generated paragraph quality and topic alignment.

Designed and tested prompt structures for AI-generated blog content using GPT-4 and Gemini. Evaluated the accuracy, tone, and relevance of model responses. Scored and ranked multiple outputs for consistency, clarity, and engagement. Provided feedback to improve AI-generated paragraph quality and topic alignment.

2024

SmartCity Chatbot – LLM Prompt Testing & Evaluation

OtherTextText GenerationEvaluation Rating
Labeled and evaluated chatbot responses from GPT-based models for municipal question-answering. Tasks included ranking AI outputs by quality, annotating unclear or misleading completions, and scoring conversation success. Helped improve prompt templates and trained the bot to better handle user intent across government service topics.

Labeled and evaluated chatbot responses from GPT-based models for municipal question-answering. Tasks included ranking AI outputs by quality, annotating unclear or misleading completions, and scoring conversation success. Helped improve prompt templates and trained the bot to better handle user intent across government service topics.

2024

Education

S

School not specified

Prompt Engineering

Not specified
2025 - 2025
Q

Queen's University

Bachelor of Arts with Honors, Economics

Bachelor of Arts with Honors
2026

Work History

Q

Queen's Student Constables

Supervisor

Kingston
2023 - Present
Q

Queen's University – ResLife

Residence Don

Kingston
2022 - Present