Who is Vinamra Sharma?

Vinamra Sharma is a PhD student at the University of Glasgow researching AI compilers and adaptive optimization for edge devices. He is also an AI Engineer at Unineed Limited and the founder of mcurio.com, a platform for equitable AI education.

What does Vinamra Sharma research?

Vinamra Sharma researches AI compilers, specifically transfer learning for adaptive compiler optimization in edge devices. His work focuses on making AI systems more efficient and accessible across diverse hardware platforms, with recent publications on biases in edge language models and efficient tiny machine learning for human activity recognition.

mcurio.com is an educational platform founded by Vinamra Sharma that focuses on building equitable AI education for all. It explores the intersection of artificial intelligence and human philosophy, providing resources and community for those interested in understanding AI from both technical and philosophical perspectives.

How can I collaborate with Vinamra?

You can connect with Vinamra Sharma through email (vinamrasharma5@gmail.com), LinkedIn (linkedin.com/in/vinamra-sharma), or by reaching out through his website. He is open to research collaborations, hackathon partnerships, and discussions about AI, technology, and innovation.

Vinamra Sharma

PhD Candidate (AI Compilers) | AI Engineer | Hackathonist

University of Glasgow || Unineed Limited, UK

Hi, I'm Vinamra (aka Vin), a PhD candidate in the School of Computing Science at the University of Glasgow, researching AI compilers and efficient inference for constrained hardware under the supervision of Dr José Cano Reyes.

Beyond academia, I work as an AI Engineer at Unineed Limited, where I build end-to-end AI systems and automation pipelines with measurable business impact. I also use hackathons as a rapid experimentation lab for real-world problems. To date, I’ve participated in 110+ hackathons and won 65+ awards, collaborating with 550+ people across 38+ countries.

My interests lie in AI Compilers, EdgeAI, Ethical AI, and LLM Systems.

I believe free, quality education is a fundamental right for every human being; therefore building: Mcurio. I care about the environment; so developing ClimateThread.

I'm always open and excited to connect with like-minded people and collaborate on projects, hackathons, or research; feel free to reach out at v.sharma.3@research.gla.ac.uk. I'd love to hear from you!

View Research Explore Projects Download Resume

Latest News & Publications

Stay updated with my latest research, entrepreneurial ventures, and thoughts on AI, technology, and innovation.

News Timeline

[May '26]
Accepted to attend the ACACES Summer School (organized by HiPEAC) with a full grant (€1,400). I will attend 12–18 July 2026 in Fiuggi, Italy.
[Apr '26]
Project "Coire" won the Grand Prize (CAD $1000) at The Climate Change-Makers Challenge: 2026 — an offline disaster-response app built in Flutter with Bluetooth-based peer-to-peer communication.View on Devpost
[Mar '26]
Workshop paper "LLM-Driven Design Space Exploration of FPGA-based Accelerators" has been accepted at EuroSys '26InSyDe
[Mar '26]
Project "TechEdge: A Platform for Teacher-Guided Distillation of On-Device Language Models" has been shortlisted for theIEEE IES Generative AI Challenge 2026 Hackathon
[Jan '26]
Pushed the new website frontend live and made the source code fully open-source on GitHub.View on GitHub

Recent Publications

View all on Google Scholar

LLM-Driven Design Space Exploration of FPGA-based Accelerators

Vinamra Sharma, Xingjian Fu, Jude Haris, José Cano

Workshop on Intelligent System Design (InSyDe), co-located with EuroSys '26 • 2026

View Paper

EdgeAI Models for Human Activity Recognition on Low-Power Devices

Vinamra Sharma, Danilo Pau, José Cano

Seventh UK Mobile, Wearable and Ubiquitous Systems Research Symposium (MobiUK 2025) • 2025

University of Edinburgh • July 7-8, 2025

View Abstract

Biases in Edge Language Models: Detection, Analysis, and Mitigation

Vinamra Sharma, Danilo Pietro Pau, José Cano

arXiv preprint • 2025

EDGE AI Research Symposium 2025 • 2025

View Paper

Best Paper in Track Award

Efficient Tiny Machine Learning for Human Activity Recognition on Low-Power Edge Devices

Vinamra Sharma, Danilo Pau, José Cano

2024 IEEE 8th Forum on Research and Technologies for Society and Industry Innovation (RTSI) • 2024

IEEE • 2024

View Paper

Best Paper Award

Phishing prevention techniques: past, present and future

Himanshu Gautam, Vishal Kumar, Vinamra Sharma

Proceedings of Integrated Intelligence Enable Networks and Computing: IIENC 2020 • 2021

Springer • 2021

View Paper

Best Paper Award

Institutional Recommendation and Ranking System Based on Integrated Datasets and Analysis

Vishal Kumar, Akanksha Joshi, Vinamra Sharma

2020 International Conference on Advances in Computing and Communication Engineering (ICACCE) • 2020

IEEE • 2020

View Paper

Awards & Recognition

Grand Prize Winner (CAD $1000) - The Climate Change-Makers Challenge 2026 - Awarded for project: 'Coire'

College Scholarship - School of Computing Science, University of Glasgow - Awarded for 3.5 Years of PhD

Best of the Rest Award Winner - Climate Change Maker Challenge 2025

3rd Prize - Animal Hacks 2025

Winner - AI in the Outback

Best Paper in Track Award - IEEE RTSI 2024

Employee of the Month Award - Unineed Limited

2nd Prize - Poster Presentation by IEEE

Selected as Youth STEM Changemaker - Youth STEM 2030

Best Pitch Award - Pitch for Earth, Sweden

Winner - Hack for Earth 2023 (Invited to work with UNICEF)

Runner-up - Amazonia Hack (Earth Hacks, Brazil)

Runner-up - Code to Give (Morgan Stanley, UK)

Winner - FDM Design Challenge (Glasgow, Scotland)

Mystery Award Winner - The Climate Change Maker 2023

Best Chinachem Group Award - PolyHack 2023 (China)

Best of the Rest Award - The Climate Change Maker (YIC, Canada)

Design Your Future Award - MakeUC (University of Cincinnati)

Winner - Amazonia Hack 1.0

First Position - Healthcare Ideation at MED INVADE 2022 (SMR, India)

Merit Based Scholarship - Awarded for consistently standing among the top 1% of the class and scoring high in academics

Finalist VARCoE - IIT Bhubaneswar - Selected in the top 34 AR/VR startups throughout the country and presented the final presentation to the jury

Regional Finalist CHUNAUTI-2.0 - Selected for the project entitled: 'Prakrit'

Winner HackDuke 2021 - Awarded for project entitled: 'NeuroMatter: An Integrated Platform To Spread & Sustain Equality and cure neurological disorders'

Winner HackTCMX 1 - Awarded for project entitled: 'iAid: Providing first aid advice in emergency situations'

Winner BioHacks2021 - Awarded by University of California Riverside, USA for the project entitled: 'Roots: A Green Social Media'

Winner MakeMIT2021 - Awarded by the Massachusetts Institute of Technology, USA for the project entitled: 'SpreadRo: A Multipurpose Rover For The Future'

Runner-up Synaptic Hacks - Awarded for the research proposal on combating the neurological disorders consuming advance and complex technologies entitled: 'Heal-Era'

Inequality Track Winner & Best Media Hack Award - HackDuke (Duke University, USA)

Best Research Paper Award - Awarded by the program committee of Proceedings of Integrated Intelligence Enable Networks and Computing (2021), Springer for the presentation of research entitled: 'Phishing Prevention Techniques: Past, Present and Future'

All India Rank 12 - Awarded by IEEEXtream 14.0 for securing a national rank of twelve, in twenty-four hour long competitive programming hackathon

Best Research Paper Award - Awarded by the organising committee of International Conference on Advances in Computing and Communication Engineering (2020), IEEE for the presentation of research paper entitled: 'Institutional Recommendation and Ranking System Based on Integrated Datasets and Analysis'

All India Rank 26 - Awarded by IEEEXtream 13.0 for securing a national rank of twenty-six, in twenty-four hour long competitive programming hackathon

Merit Based Scholarship - Awarded for consistently standing among the top 1% of the class and scoring high in academics