Haritha Thilakarathne

Cloud Solution Architect @ Microsoft · Researcher · Speaker · Blogger

I am a seasoned professional in the field of Data and AI, with extensive research and practical experience in machine learning, deep learning, computer vision, and the Microsoft Azure AI stack, along with a proficiency in developing intelligent applications.

As a Cloud Solution Architect at Microsoft, I design and implement scalable, secure, and intelligent cloud architectures that transform business operations and deliver cutting-edge AI capabilities on Azure. My dedication to AI has been recognized by Microsoft, which has honored me as a Most Valuable Professional in Artificial Intelligence for eight consecutive years.

I earned my Ph.D. in Deep Learning with a collaboration with the Australian Institute of Sport at La Trobe University, Australia. Being an active contributor to the technical community, I regularly host sessions at technical conferences and user group meetups, focusing on AI-related technologies. I maintain a blog where I share my experiences and experiments in deep learning and cognitive computing.

Research Interests : Deep Learning, Computer Vision, Artificial Intelligence, Responsible AI


Timeline

Cloud Solution Architect - Azure AI

Microsoft
August 2024 - Present

Lead Consultant

Kodez
January 2024 - July 2024

Consultant (Data & AI)

Arinco
April 2022 - September 2023

Graduate Researcher

La Trobe University, Australia
July 2018 - January 2022

AI Specialist

Vevro
February 2018 - July 2018

Engineer - Data Science & Analytics

Tech One Global Ltd
August 2016 - February 2018

Intern - Developer Experience

Microsoft
January 2016 - July 2016



Interests

Apart from being an AI researcher, I enjoy most of my time being outdoors. I enjoy hiking, camping, and nature photography. Can explain myself as a travel addict, ready to hit the road at any time with the backpack.

When forced indoors, I do enjoy writing free style poems and short stories, I am an aspiring chef, and I spend a large amount of my free time exploring the wonderful spices in my kitchen.


Publications

Group Activity Recognition using Unreliable Tracked Pose [Read]
H Thilakarathne, A Nibali, Z He, S Morgan, Neural Computing & Applications (2024)

Pose is all you need: The pose only group activity recognition system (POGARS) [Read]
H Thilakarathne, A Nibali, Z He, S Morgan, Machine Vision and Applications 33, 95(2022)

Predicting Floods in North Central Province of Sri Lanka using Machine Learning and Data Mining Methods. [Read]
H Thialakarathne, K Premachandra, Proceedings of the 12th Annual Sessions, Sri Lanka Association for Artificial Intelligence 2017.

Improving Assessment on MOOCs through Peer Identification and Aligned Incentives. [Read]
Gamage D,Whiting ME,Rajapakshe T,Thilakarathne H,Perera I et al., L@S 2017 - Proceedings of the 4th (2017) ACM Conference on Learning at Scale.

Daemo: A Self-Governed Crowdsourcing Marketplace. [Read]
Stanford HCI Research Group, UIST 2015 - Adjunct Publication of the 28th Annual ACM Symposium on User Interface Software and Technology.


Awards

  • Microsoft Most Valuable Professional (AI) - 2024
  • Microsoft Most Valuable Professional (AI) - 2023
  • Microsoft Most Valuable Professional (AI) - 2022
  • Microsoft Most Valuable Professional (AI) - 2021
  • Microsoft Most Valuable Professional (AI) - 2020
  • Microsoft Most Valuable Professional (AI) - 2019
  • Microsoft Most Valuable Professional (AI) - 2018
  • Microsoft Most Valuable Professional (AI) - 2017