Prishita Ray
Research Assistant at The Johns Hopkins University
Washington DC-Baltimore Area United States
Summary
👤
Senior🎓
Top SchoolPrishita Ray is a research-focused software engineer with 8 years of experience blending machine learning, reinforcement learning, and large-scale data engineering across academia and industry. Currently at Johns Hopkins CDHAI, she applies RL, inverse bandits, and LLMs to personalize patient messaging and prescription generation, building on prior roles that ranged from production data pipelines at American Express to on-device voice AI at Samsung. Her MEng in Computer Science from Cornell and a BTech from VIT underpin a track record of research internships (IISc, ISRO) and open-source contributions such as a GSoC project for FrameNet Brasil that modernized image/video annotation tooling. Comfortable moving models from prototype to product, she also has practical experience with PySpark, Hive, container security, and signal processing for SAR and audio data.
8 years of coding experience
1 year of employment as a software developer
Bachelor of Technology - BTech Computer Science and Engineering, Bachelor of Technology - BTech Computer Science and Engineering at Vellore Institute of TechnologyMaster of Engineering - MEng Computer Science, Master of Engineering - MEng Computer Science at Cornell UniversityHigher Senior Secondary School Mathematics and Computer Science, Higher Senior Secondary School Mathematics and Computer Science at CMR National Public School, Bangalore
Bengali, English, Hindi, French
Stackoverflow
37reputation
6kreached
0answers
3questions
Github Skills (70)
regression10
pytorch9
automatic-differentiation9
simulations8
autoencoder8
scientific-computing8
python8
gpu8
machine-learning8
autodiff8
metasploit8
jit8
composable8
simulator7
deep-learning7
Programming languages (7)
Github contributions (5)
PRISHIta123/DSER_Movie_Subtitles
Mar 2020 - Mar 2024
Contributions:6 pushes, 1 branch, 1 comment in 4 years
PRISHIta123/RAELN
Dec 2019 - Jan 2022
L2-Regularized Autoencoder Enabled Ladder Networks (RAELN) for multi-class classification of network intrusion malware.
Contributions:3 releases, 142 commits, 1 PR in 2 years 1 month
autoencoderintrusionmulti-class-classificationanalysisladder
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.