Core Java • Backend • AI • Practical engineering
~/portfolio/rishit-kar
$ AI Engineer / Software Engineer / Loves Playing With Data
Third-year undergraduate at DJ Sanghvi College of Engineering, Mumbai University, with research collaborations spanning medical AI, multimodal learning, and engineering optimization.
GitHub, LinkedIn, LeetCode, Codeforces, and Google Scholar linked below.
About
I am Rishit Kar, a third-year undergraduate student at DJ Sanghvi College of Engineering, Mumbai University, with a strong passion for research and innovation in Artificial Intelligence. I am especially interested in backend systems, FastAPI, Docker, and practical machine learning systems that can be deployed in real-world settings.
Through research collaborations with IIT Patna and IIT Mandi, I have built hands-on experience in explainable medical AI, multimodal learning, and geometric deep learning for engineering systems, while strengthening my foundation in Core Java and CS fundamentals.
Education
BTech, Computer Engineering
Coursework: Artificial Intelligence, Compiler Design and Automata, Advanced Database Management Systems, Database Management Systems, Operating Systems, Data Structures, Analysis of Algorithms, Python Programming, Object-Oriented Programming Systems.
Position of Responsibility:
Research Head at DJS ACM - mentoring students on research opportunities and AI-focused academic growth within the college community.
Experience
Research Collaborator, Deep Learning for Medical Imaging.
• Worked with multimodal data, EHR text and CXR to build temporal and global graphs for deep learning-based disease phenotyping
• Focusing on explainability and clinical interpretability for medical AI applications
Supervised by Dr. Joydeep Chandra
Research Intern, Machine Learning for Propeller Optimization.
• Collaborated at the Center for Artificial Intelligence and Robotics (CAIR Lab)
• Conducted extensive literature review on geometric deep learning methodologies
• Successfully implemented Dynamic Graph Convolutional Neural Network (DGCNN) architecture
Supervised by Dr. Jagadeesh Kadiyam
Projects
Deep learning framework for robust and explainable multi-omics cancer subtype classification
Built OMNIGATE for multi-modal cancer subtype classification using mRNA, miRNA, CNV, and methylation data, with dynamic context gating, multi-objective optimization, and biomarker-focused explainability.
Developer-focused CLI/TUI clipboard manager with real-world adoption on PyPI
Built a cross-platform clipboard manager with persistent history, interactive search, restore workflows, and a TUI, later published on PyPI with 2300+ downloads.
Deep learning ensemble for medical image classification using CNN, ResNet, and Graph Neural Networks
Built a pneumonia classification pipeline from chest X-ray images using custom CNN, ResNet, and GAT models with TensorFlow and Keras.
High-performance reliable transport protocol with sliding window flow control
Engineered a reliable transport protocol with TCP-like flow control, retransmission, SHA-256 checksums, and stronger throughput than stop-and-wait approaches.
Privacy-focused VS Code extension for cleaning tracking parameters from URLs
Built a VS Code extension that removes tracking parameters from pasted URLs using lightweight offline regex-based logic.
Publications
Venue: ICLR, 2026 MemAgents Workshop, Brazil
Authors: Pearl Mody, Mihir Panchal, Rishit Kar, Kiran Bhowmick, Ruhina Karani
Status: Published
Venue: To be decided
Authors: Rishit Kar, Ved Ambulkar, Sargam Nagar, Varun Shenai, Ruhina Karani
Status: Ongoing
Talks
Venue: IDfy Company | Hosted by: Mumpy
Delivered a PySpark session covering architecture, code layout, and big data workflows for 30+ students and professionals.
Venue: Google Meet | Hosted by: ACM College Committee
Conducted a session on strategic cold mailing, profile building, and research outreach, while mentoring 15+ research mentees.
Skills
Programming Languages Python, Java, JavaScript, C, SQL (MySQL), HTML/CSS
Machine Learning & AI TensorFlow, Keras, PyTorch, Scikit-Learn, Pandas, NumPy, Matplotlib
Computer Vision & Models OpenCV, MediaPipe, CNN, ResNet, Graph Neural Networks, Variational Autoencoders
Developer Tools & Platforms Git, GitHub, VS Code, Visual Studio, Google Colab, Jupyter, Vercel, Streamlit, pytest
Technical Knowledge Operating Systems, DBMS, Advanced DBMS, UDP/TCP, socket programming, DSA, software engineering
Contact
Open to research opportunities, software roles, and meaningful AI collaborations.
