# Ishan Rahul Surdi

> Computer Science undergraduate at MIT World Peace University, Pune (graduating 2027), working on applied machine learning, AI security, quantum-inspired optimization and open-source engineering.

Personal site with research, projects and articles. Contact: ishansurdi2105@gmail.com

## Pages

- [Home / portfolio](https://www.ishansurdi.com/): about, education, experience, research, projects, contact
- [Articles](https://www.ishansurdi.com/articles.html): research notes and writing

## Research

- **A Hybrid XGBoost-CNN-1D Framework for Workload-Aware HPC in Cloud System** — Research paper, 2026; Under review; submitted to International Journal of Computing; under the guidance of Dr. Prathamesh Lahande (DES Pune University)
  Combines XGBoost and a 1-D CNN with recall-union fusion to flag high-work jobs from workload traces and route them across cloud VMs.
- **TAC-Net: Transition-Aware Adaptive Computation for Efficient Tabular Neural Networks** — Research paper, 2026; Under review; submitted to Inteligencia Artificial; under the guidance of Dr. Sachin Bhoite (Dr. Vishwanath Karad MIT World Peace University)
  A learned gate decides, layer by layer, whether deeper computation would fix or harm the current prediction. Preserved accuracy in 13 of 15 runs while cutting executed computation by 36–55%.
- **Prediction-Guided Rebuilding of Dynamic Vector Indexes for AI Agent Memory** — Conference paper, 2026; Submitted; submitted to 2027 International Conference on Emerging Smart Computing and Informatics (ESCI); under the guidance of Dr. Sachin Bhoite (Dr. Vishwanath Karad MIT World Peace University)
- **Are quantum computers a threat to privacy?** — Journal article, 2023; Published; published in International Journal for Research in Applied Science and Engineering Technology (IJRASET) [DOI 10.22214/ijraset.2023.55568](https://doi.org/10.22214/ijraset.2023.55568)

## Projects

- [EpiSentinel](https://github.com/ishansurdi/EpidemicIntelligence): Disease outbreak forecaster combining Neural ODEs with graph attention networks over data from 201 countries. Finalist at the IIT BHU hackathon. Stack: Python, PyTorch, Neural ODE, GNN. Live demo: https://episentinel-frontend.onrender.com
- [AegisKYC](https://github.com/ishansurdi/AegisKYC): Multilingual OCR pipeline for detecting fraudulent identity documents in KYC workflows. 98.5% accuracy on the internal evaluation set. Stack: Python, OCR, Scikit-learn.
- [SkyQuery AI](https://github.com/ishansurdi/skyquery-ai): Retrieval-augmented generation pipeline grounded in a Neo4j knowledge graph, with structured query decomposition. Graph-grounded answers instead of free-floating LLM output. Stack: Python, Neo4j, RAG, LLMs.
- [SDK-Sovereign](https://github.com/ishansurdi/SDK-Sovereign): Multi-agent OpenEnv environment where a Lead and an Auditor agent coordinate over seven turns to migrate code off a cut-off vendor SDK onto a sovereign allow-list. Live on Hugging Face Spaces with a playable demo and a reproducible training notebook. Stack: Python, Multi-agent RL, OpenEnv, Hugging Face. Live demo: https://ishansurdi-sdk-sovereign.hf.space/play
- [E-DERA](https://github.com/ishansurdi/AI-Economic-Distress-Early-Warning-Radar): Financial risk scoring platform with explainable features and a clean analyst-facing dashboard. End-to-end: ingestion, scoring, and reporting. Stack: Python, Pandas, Streamlit.
- [Image Quality Analyzer](https://github.com/ishansurdi/Image-Quality-Analyzer): Full-stack app that scores uploaded images 0–100 and flags blur, noise, compression, and under/over-exposure using computer vision and a trained classifier. Trained on BSDS500 and KADID-10k; deployed with a public API. Stack: Python, FastAPI, OpenCV, Scikit-learn. Live demo: https://analyzeimage.onrender.com/

## Articles

- [Hello, I'm Ishan](https://www.ishansurdi.com/articles/introduction.html): A short introduction: who I am, what I work on, and what I plan to write about here.

## Profiles

- [GitHub](https://github.com/ishansurdi)
- [LinkedIn](https://www.linkedin.com/in/ishansurdiofficial/)
- [ResearchGate](https://www.researchgate.net/profile/Ishan-Surdi?ev=hdr_xprf)
- [Medium](https://medium.com/@ishansurdi)
- [Email](mailto:ishansurdi2105@gmail.com)
- [X (Twitter)](https://x.com/cusrious_minds)
- [ORCID](https://orcid.org/0009-0005-4335-5420)

## Optional

- [Full text of this site for LLMs](https://www.ishansurdi.com/llms-full.txt)