Prarthana Bhattacharyya
Machine Learning Engineer @Eedi
Signup · Get unlimited contacts
WORK HISTORY
Machine Learning Engineer @Eedi
London, GB
Developing and deploying ML and Gen-AI solutions across UK, US and Indian schools. Working across data analysis, data curation, evaluation design, model research, model iteration, deployment, and operationalization. Benchmarked LLMs against small custom models to evaluate scalability, accuracy, speed, and cost for Eedi\'s product. Deployed a generative (VAE)-based next-best question selector for dynamic quizzes in schools. Productionized on Azure using LitServe, Terraform, and GitHub Actions. Developed customized LLM-based misconception diagnosis from dialog, enabling automated diagnosing of gaps in student mathematical reasoning. Presented at \'Learning at Scale\' conference, 2026. Leading AI tutor evaluation: building LLM-as-Judge pipeline to assess safety and tutor response quality. Resolved critical production issues including memory scaling bottlenecks, through systematic load testing, model profiling and model optimization.
EDUCATION
The University of Tokyo
Master of Science - MS(Thesis)
Jadavpur University
Bachelor of Engineering - BE (Hons.)
Bharatiya Vidya Bhavan's
CBSE, High School
University of Waterloo
Doctor of Philosophy - PhD
ABOUT PRARTHANA BHATTACHARYYA
I\'m a Machine Learning Research Engineer at Eedi, specializing in building practical ML solutions that bridge cutting-edge research and real-world applications. With 7+ years of experience spanning autonomous driving, wearable AI, and education technology, I focus on developing efficient, deployable models that solve complex problems. My research has been recognized with a Best Paper award at ECCV-2024 Smart Eyewear Workshop and cited 450+ times, with open-source contributions achieving 400+ GitHub stars. My work has been demonstrated at major industry events including AWE-USA and CES. I\'m a UK Global Talent awardee with unrestricted right to work in the UK. I hold a Ph.D. in Electrical and Computer Engineering from the University of Waterloo (Canada) and a Master\'s from the University of Tokyo (Japan). I speak English, Bengali and Hindi fluently, with a N2 certification (business-level) in Japanese proficiency.Current Focus: At Eedi, I develop models that improve personalized learning at scale. My work combines educational and generative AI with practical MLOps to deliver measurable impact for students and educators.Research Interests: Event-Based Vision and Wearables: Pioneered ultra-low power gesture recognition systems for smart eye-wear, achieving state-of-the-art accuracy at only 6mW power consumption. Autonomous Driving: Developed learning approaches for motion forecasting and 3D object detection, enabling robust perception in complex urban environments. Efficient ML: Specializing in building high-performance models with practical constraints like low power, limited data, real-time deployment. My ML work has been shipped in production for ROLI\'s AI music tutor applications.Technical Expertise: Deep learning frameworks (PyTorch, TensorFlow, Keras), MLOps platforms (AWS, Azure, MLFlow, ClearML), 3D computer vision, self-supervised learning, graph neural networks, and event-based vision.Opinions are personal and do not reflect that of my employer.
This profile is compiled from publicly available professional sources. Unifers is not affiliated with or endorsed by LinkedIn. Request removal of this profile.