ANSHUL PATIL Backend & Systems Developer | GSoC @ BRL-CAD Mumbai, Maharashtra | anshulpatil1022@gmail.com https://github.com/AnshulPatil2005 | https://www.linkedin.com/in/anshul-patil-575006280/ ======================================================================== SUMMARY ======================================================================== I build distributed systems and AI infrastructure: open-source geometry processing, document intelligence pipelines, and production-grade developer tools. Currently pursuing B.Tech at IIIT Surat and contributing to BRL-CAD via Google Summer of Code. ======================================================================== EDUCATION ======================================================================== B.Tech, Indian Institute of Information Technology, Surat 2024 – 2028 ======================================================================== EXPERIENCE ======================================================================== Selected Contributor, Manifold Subproject — Google Summer of Code, BRL-CAD Present | https://summerofcode.withgoogle.com/ - Selected to improve BRL-CAD's Manifold C++ geometry processing library through CI reliability and benchmarking infrastructure. - Designed cross-platform determinism checks using fixed mesh cases, canonical artifacts, SHA256 comparison, and clear mismatch reporting. - Planned Linux Clang ASan+UBSan testing and PR/weekly benchmark workflows with base-vs-head comparison, JSON history, and dashboard trend visualization. Open Source Contributor, AI Systems — Extralit Open Source Dec 2025 – Present | https://github.com/extralit/extralit - Contributed to an AI document intelligence platform supporting OCR parsing, dataset workflows, structured extraction, and annotation pipelines. - Merged 10+ pull requests across ingestion pipelines, dataset configuration, frontend components, validation logic, and test coverage. - Fixed multi-step workflow persistence issues and added structured table-based dataset inputs with validation and UI integration. Software Engineer Intern — Bluestock™ Dec 2025 – Feb 2026 | https://bluestock.in/ - Improved system reliability and performance across user-facing financial features. - Wrote clean, well-tested code and performed debugging across the codebase. - Collaborated remotely with the team over a 3-month internship engagement. Software Developer Intern — Techvisio Design May 2025 – Aug 2025 | https://www.techvisio.in/ - Built a full-stack analytics dashboard using React, Django REST Framework, and SQL APIs to process 10K+ daily user events. - Integrated AWS S3 pipelines for 300K+ monthly records and reduced backend API latency by 40% through query optimization and caching. ======================================================================== PRODUCTS ======================================================================== Stratum — AI code intelligence, deployment risk, incident correlation https://anshulpatil.is-a.dev/stratum - Reviews GitHub pull requests with typed findings, risk scoring, per-file summaries, review modes, async jobs, reruns, comparisons, and exports. - Analyzes deployment batches to detect semantic conflicts between PRs before they are shipped together. - Builds a live architecture-drift view from accumulated review data, highlighting risky modules, boundary erosion, and refactor pressure. - Correlates Sentry, Render, and Railway production errors with recently reviewed PRs using file/module overlap, recency, severity, and cross-service co-incidence signals. docRAG v3 — PDF RAG, OCR, semantic search, research GraphRAG https://github.com/AnshulPatil2005/docRAG_v3 - Processes PDF uploads asynchronously with FastAPI, Celery, Redis, OCR, sentence-transformer embeddings, and Qdrant vector search. - Supports natural-language chat over documents with citations that point back to source document chunks and pages. - Includes an Angular frontend for upload, task status tracking, health checks, recent tasks, and document query workflows. - Adds research-paper intelligence foundations: ontology validation, paper parsing, citation normalization, and entity extraction for graph construction. ======================================================================== SELECTED PROJECTS ======================================================================== AI Pull Request Reviewer — FastAPI, React, TypeScript, GitHub API, OpenRouter https://ai-pr-reviewer-theta.vercel.app/ Full-stack AI pull request reviewer that fetches GitHub PR diffs, runs LLM-assisted risk analysis, persists review history, and returns structured findings, suggestions, per-file summaries, and exportable review reports. Open-source and self-hostable; its architecture became the foundation Stratum was built on. sect_scrape — Python, Playwright, BeautifulSoup, SQLite, OCR https://github.com/AnshulPatil2005/sect_scrape Research-grade scraper for Gujarat eCourts disposed CRMA/JMFC cases, focused on CrPC sections 436, 437, 438, and 439. It automates the eCourts portal with Playwright, handles CAPTCHA/OCR support, stores structured metadata in JSON/JSONL/SQLite, and preserves source HTML/PDF orders for verification. Faulty Node Detection — NS-3, Python, anomaly detection, HTML dashboard https://github.com/AnshulPatil2005/faulty_node_detection Four-stage faulty-node detection pipeline for simulated networks. It builds a 12-node NS-3 topology, injects packet-loss/high-delay/low-bandwidth faults, extracts FlowMonitor features, detects anomalies with z-score/IQR/composite scoring, and explains results through an interactive HTML dashboard with an LLM diagnostic agent. Codeforces — FastAPI, React, TypeScript, Codeforces API https://github.com/AnshulPatil2005/codeforces Modern full-stack Codeforces dashboard for contest profiles, rating visualizations, performance insights, and problem browsing. The backend uses FastAPI with rate limiting and caching around real Codeforces data; the frontend uses React, TypeScript, Tailwind, React Query, and Recharts. Smartfolio — Python, portfolio analytics, automation https://github.com/AnshulPatil2005/Smartfolio Python project around smarter portfolio analysis and automation. It shows backend-oriented product thinking applied to financial/portfolio workflows where data processing and decision support matter. IL-TUR — Jupyter Notebook, NLP, model experimentation https://github.com/AnshulPatil2005/IL-TUR Notebook-based machine learning/NLP experimentation repository. It is useful recruiter evidence for data preparation, exploratory modeling, evaluation, and research-style iteration. ======================================================================== OPEN SOURCE ======================================================================== browser-use | https://github.com/AnshulPatil2005/browser-use Fork of the browser-use automation project, which focuses on making websites accessible to AI agents. sugar-org/swarm-external-secrets | https://github.com/sugar-org/swarm-external-secrets Docker Swarm external secrets provider plugin for integrating Swarm workloads with external secret stores such as Vault. Extralit/extralit | https://github.com/Extralit/extralit Open-source AI document intelligence platform for systemic data extraction with LLM assistance. BiniWorld/Hyperledger-BiniBFT | https://github.com/BiniWorld/Hyperledger-BiniBFT Go-based open-source work around Hyperledger/BFT infrastructure. qbtrix/soul-protocol | https://github.com/qbtrix/soul-protocol Open standard for portable AI identity, memory, and emotion across AI companions. elalish/manifold | https://github.com/elalish/manifold C++ geometry library focused on topological robustness, used for mesh operations and geometry processing. Generated from anshulpatil.is-a.dev — the site and this file share one source.