For employers

Hire this AI Trainer

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

Invite to Job
Kalana Senevirathne

Kalana Senevirathne

AI and Automation Specialist - Computer Vision & Workflow Optimization

SRI_LANKA flag
Matale, Sri Lanka
$30.00/hrExpertCVAT

Key Skills

Software

CVATCVAT

Top Subject Matter

No subject matter listed

Top Data Types

ImageImage

Top Label Types

Bounding Box

Freelancer Overview

I am a self-taught AI and automation enthusiast with hands-on experience in data annotation, computer vision, and workflow optimization. I have developed and automated data labeling pipelines using Python, OpenCV, YOLOv5/v8, and browser automation tools like Tampermonkey and Puppeteer, primarily for image detection and annotation tasks. My background includes designing human-in-the-loop systems, implementing error tracking, and documenting technical processes in English to support reproducibility. I am detail-oriented, logical, and comfortable working with both Linux and Windows platforms, and I am eager to contribute my skills to remote AI training data projects.

ExpertEnglish

Labeling Experience

CVAT

Semi-Automated Data Pipeline (CVAT + YOLOv8)

CVATImageBounding Box
The Blueprint (Goal): Creating a high-precision dataset for detecting objects in a manufacturing environment. The goal was to reduce the time and cost of manual annotation without sacrificing accuracy. The Process (How I solved it): Instead of manually drawing every box, I architected a "Human-in-the-Loop" workflow—think of it like an assembly line where a robot does the heavy lifting and I act as the Quality Control Inspector. Auto-Labeling (The Robot): I ran raw images through a custom YOLOv8 model I trained to generate the initial bounding boxes automatically. Verification (The Inspector): I imported these pre-labeled images into CVAT. My role shifted to verifying the AI's work and fixing edge cases, rather than drawing from scratch. Final Output: Cleaned and exported the validated dataset in YOLO format for final training. The Result: This semi-automated approach increased annotation speed by 5-6x compared to standard manual labeling, delivering a production-ready

The Blueprint (Goal): Creating a high-precision dataset for detecting objects in a manufacturing environment. The goal was to reduce the time and cost of manual annotation without sacrificing accuracy. The Process (How I solved it): Instead of manually drawing every box, I architected a "Human-in-the-Loop" workflow—think of it like an assembly line where a robot does the heavy lifting and I act as the Quality Control Inspector. Auto-Labeling (The Robot): I ran raw images through a custom YOLOv8 model I trained to generate the initial bounding boxes automatically. Verification (The Inspector): I imported these pre-labeled images into CVAT. My role shifted to verifying the AI's work and fixing edge cases, rather than drawing from scratch. Final Output: Cleaned and exported the validated dataset in YOLO format for final training. The Result: This semi-automated approach increased annotation speed by 5-6x compared to standard manual labeling, delivering a production-ready

2025 - 2025

Education

S

St. Thomas College

General Certificate of Education Advanced Level, Combined Mathematics, Physics, Chemistry, English

General Certificate of Education Advanced Level
2020 - 2020
C

Christ Church National School

General Certificate of Education Ordinary Level, Mathematics, Science, Information Technology

General Certificate of Education Ordinary Level
2016 - 2016

Work History

A

AbsolitAI

Senior AI Systems Architect & MLOps Engineer

Colombo
2024 - Present