Rishik Sarkar

M.Eng. Computer Science at Cornell University
B.S. Computer Science at Rutgers University
B.S. Cognitive Science at Rutgers University

Specializing in NLP-driven mental healthcare solutions

About

“If you could train an AI to be a Buddhist, it would probably be pretty good.”
- Reid Hoffman

I am currently pursuing a Master of Engineering in Computer Science at Cornell University. Prior to this, I graduated Summa Cum Laude with honors from Rutgers University-New Brunswick with a B.S. in Computer Science and Cognitive Science and was inducted into Phi Beta Kappa. I also worked as an ML Full-Stack Developer Intern at a fintech scaleup and as a research assistant at a joint Rutgers-Princeton laboratory, where I focused on data integration and machine learning.

My passions lie at the intersection of artificial intelligence and psychology, and I am keen to explore computational linguistics, cognitive neuropsychiatry, and new LLM frameworks for natural language understanding, including transformer models and fine-tuning for sentiment and emotional analysis. In the future, I aim to establish a startup and develop NLP-driven solutions in the mental healthcare space.

Documents

Check out my professional experience and qualifications:

Experience

Oct 2024 - Nov 2024

Software Engineer (Contract)AllAboutID

Built a secure asset management system for an interior design startup, integrating MongoDB Atlas for data storage and SVG handling for furniture assets, with a Next.js and Tailwind CSS frontend to enhance asset display and user experience.

MongoDBNext.jsTypeScriptNode.js
Sep 2023 - Aug 2024

Research AssistantPrinceton University

Developed Python scripts to consolidate data from 800+ files into an SQLite database, automating schema generation, and created a Tkinter-based GUI to facilitate custom SQL queries and database interactions for researchers.

PythonPandasSQLiteTkinterResearch
Jun 2023 - Dec 2023

ML Full-Stack Developer InternProvenir

Collaborated with an AI team to develop an end-to-end credit risk decisioning pipeline, utilizing machine learning and deep learning techniques to achieve 95% model accuracy and enhance explainability while improving software reliability through over 100 unit tests.

scikit-learnTensorFlowFLAMLKubernetes
May 2022 - Jun 2023

ML Research InternAbraira Lab

Created a high-quality dataset of 10,000+ samples using Motion Sequencing for an unsupervised ML model in a study on spinal cord injuries in mice, enhancing data accuracy by analyzing and correcting behavioral patterns.

PythonMoSeq2Unsupervised LearningResearch

Projects

Tap nodes to explore