For employers

Hire this AI Trainer

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

LoginCreate account
Invite to Job
M
Muhammad Arshad

Muhammad Arshad

Object Detection Model Trainer (YOLO)

Pakistan flagLahore, Pakistan
$10.00/hrEntry LevelOther

Key Skills

Software

Other

Top Subject Matter

Construction Site Safety
Fake News Detection (NLP)
Conversational AI / LLM Training

Top Data Types

ImageImage
TextText

Top Task Types

Object DetectionObject Detection
Fine-tuningFine-tuning
Prompt + Response Writing (SFT)Prompt + Response Writing (SFT)

Freelancer Overview

Object Detection Model Trainer (YOLO). Brings 1+ years of professional experience across complex professional workflows, research, and quality-focused execution. Core strengths include Other. Education includes Bachelor of Science, University of Central Punjab (2022) and Intermediate, Government Islamia College (2022). AI-training focus includes data types such as Image and Text and labeling workflows including Object Detection, Fine-tuning, and Prompt + Response Writing (SFT).

Entry LevelEnglishUrduPunjabi

Labeling Experience

Object Detection Model Trainer (YOLO)

OtherImageObject Detection
I designed and implemented a YOLO-based object detection system for construction site safety monitoring. The project involved training custom YOLOv5 and YOLOv8 models on annotated images of construction workers using transfer learning techniques. I evaluated the models using metrics like mAP, precision, recall, and F1-score to ensure accuracy and robustness. • Labeled images for presence of safety equipment such as helmets, vests, and gloves • Used bounding boxes to annotate relevant safety equipment in various real-world conditions • Performed manual and semi-automated label review for dataset quality assurance • Contributed to model fine-tuning and evaluation loop for increased detection accuracy.

I designed and implemented a YOLO-based object detection system for construction site safety monitoring. The project involved training custom YOLOv5 and YOLOv8 models on annotated images of construction workers using transfer learning techniques. I evaluated the models using metrics like mAP, precision, recall, and F1-score to ensure accuracy and robustness. • Labeled images for presence of safety equipment such as helmets, vests, and gloves • Used bounding boxes to annotate relevant safety equipment in various real-world conditions • Performed manual and semi-automated label review for dataset quality assurance • Contributed to model fine-tuning and evaluation loop for increased detection accuracy.

2026 - 2026

Prompt Engineer and LLM Data Trainer (Internship)

OtherTextPrompt Response Writing SFT
I worked with Large Language Models (LLMs), focusing on prompt engineering and SFT (Supervised Fine-Tuning). The tasks included writing and refining prompt-response pairs for conversational agents. I collaborated with technical teams to ensure quality and relevance of LLM responses. • Generated and annotated diverse prompt-response pairs to train conversational AI • Applied evaluation frameworks to monitor prompt understanding and response generation • Reviewed model outputs for coherence and alignment with intended use cases • Improved chatbot logic by expanding and refining training datasets.

I worked with Large Language Models (LLMs), focusing on prompt engineering and SFT (Supervised Fine-Tuning). The tasks included writing and refining prompt-response pairs for conversational agents. I collaborated with technical teams to ensure quality and relevance of LLM responses. • Generated and annotated diverse prompt-response pairs to train conversational AI • Applied evaluation frameworks to monitor prompt understanding and response generation • Reviewed model outputs for coherence and alignment with intended use cases • Improved chatbot logic by expanding and refining training datasets.

2025 - 2025

NLP Dataset Labeler and Model Fine-tuner

OtherTextFine Tuning
I built and fine-tuned BERT and LSTM-based NLP models for fake news detection. The work involved annotating text datasets for authenticity and fraudulent content. I evaluated model performance with various classification metrics. • Labeled and verified news articles as authentic or fake for supervised learning • Fine-tuned BERT models on labeled news datasets for enhanced contextual understanding • Analyzed confusion matrices and adjusted data splits for balanced learning • Assisted in reliability checking and post-labeling data validation for cleaner inputs.

I built and fine-tuned BERT and LSTM-based NLP models for fake news detection. The work involved annotating text datasets for authenticity and fraudulent content. I evaluated model performance with various classification metrics. • Labeled and verified news articles as authentic or fake for supervised learning • Fine-tuned BERT models on labeled news datasets for enhanced contextual understanding • Analyzed confusion matrices and adjusted data splits for balanced learning • Assisted in reliability checking and post-labeling data validation for cleaner inputs.

2025 - 2025

Education

G

Government Islamia College

Intermediate, Pre-Engineering

Intermediate
2020 - 2022
T

The Cathedral School

Matriculation, Matriculation

Matriculation
2007 - 2020

Work History

T

ThinkDevLabs

AI & Automation Intern

Lahore
2025 - 2025