AP
AP
Portfolio · Mumbai, MaharashtraOpen to internships

AnshulPatil

GSoC @ BRL-CAD  ·  Amazon ML Summer School

Backend & Systems Developer | GSoC @ BRL-CAD

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.

View my work→RésuméContact

I'm a B.Tech student at IIIT Surat who has interned at Techvisio Design building analytics dashboards that cut API latency by 40%, and I contribute to open-source projects like Extralit and BRL-CAD's Manifold library. My focus is distributed systems, AI infrastructure, and developer tooling.

Currently building

GSoC @ BRL-CAD

Manifold C++ geometry library

see the work →

Availability

Open to internships

Summer 2026 · Backend / Systems / AI

reach out →

Location

Mumbai, Maharashtra

UTC +5:30

#00

Experience

Google Summer of Code, BRL-CAD

Selected Contributor, Manifold Subproject

  • 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.
Extralit Open Source

Open Source Contributor, AI Systems

  • 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.
Bluestock™

Software Engineer Intern

  • 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.
Techvisio Design

Software Developer Intern

  • 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.

#02

Take a closer look

A broader set of repositories spanning scraping, systems, dashboards, and research experimentation.

sect_scrape

Research-grade scraper for Gujarat eCourts disposed CRMA/JMFC cases, focused on CrPC sections 436, 437, 438, and 439.

GitHubDetails →

Faulty Node Detection

Four-stage faulty-node detection pipeline for simulated networks.

GitHubDetails →

Codeforces

Modern full-stack Codeforces dashboard for contest profiles, rating visualizations, performance insights, and problem browsing.

GitHubDetails →

Smartfolio

Python project around smarter portfolio analysis and automation.

GitHubDetails →

IL-TUR

Notebook-based machine learning/NLP experimentation repository.

GitHubDetails →

#03

My Open Source

Making geometry infrastructure more reliable.

Improving BRL-CAD's Manifold C++ geometry processing library through CI reliability, benchmarking infrastructure, and cross-platform determinism checks.

GSoC work on CI reliability, cross-platform determinism, sanitizer workflows, benchmarking, WASM/runtime fixes, examples, and docs.

elalish/manifold →Google Summer of Code

My projects

AI Pull Request Reviewer

Repo →

Automated PR review feedback using LLMs: reduces manual review overhead by analyzing code diffs, repository context, and commit history. Built FastAPI services for diff parsing, repository inspection, prompt construction, and model fallback. GitHub webhook integration triggers analysis on new commits with no manual steps required.

Python, FastAPI, GitHub API, LLM APIs, REST APIs

Intelligent Document Processing Platform

Repo →

Parallelized document ingestion pipeline handling OCR extraction, vector embedding, and semantic search over unstructured files. Celery and Redis queue architecture enables concurrent multi-document processing. Retrieval layer uses vector embeddings for context-aware semantic search and structured information extraction.

FastAPI, Celery, Redis, Vector DB, OCR

Also contributing to

browser-use

Repo →

Fork of the browser-use automation project, which focuses on making websites accessible to AI agents.

sugar-org/swarm-external-secrets

Repo →

Docker Swarm external secrets provider plugin for integrating Swarm workloads with external secret stores such as Vault.

Extralit/extralit

Repo →

Open-source AI document intelligence platform for systemic data extraction with LLM assistance.

BiniWorld/Hyperledger-BiniBFT

Repo →

Go-based open-source work around Hyperledger/BFT infrastructure.

qbtrix/soul-protocol

Repo →

Open standard for portable AI identity, memory, and emotion across AI companions.

GitHub Activity

 
04

Research

Academic and applied research projects at the intersection of NLP, medical imaging, and machine learning systems.

Gujarati Legal Document Corpus and NLP Pipeline for Court Case Understanding

Ongoing

Building a machine learning-ready Gujarati legal corpus from Gujarat eCourts data, with NLP pipelines for classification, named entity recognition, summarization, and retrieval-augmented QA over district court judgments.

NLP/OCR/Transformers/IndicBERT/MuRIL/Python/Low-resource NLP/RAG
Read more →

Robust and Explainable CNN-Based Chest X-Ray Classification Across Unseen Clinical Datasets

Ongoing

A cross-dataset generalization study training CNN models on CheXpert and evaluating them zero-shot on MIMIC-CXR, NIH ChestX-ray14, PadChest, VinDr-CXR, and BRAX to measure architecture robustness and detect dataset-specific shortcuts.

Medical Imaging/CNN/PyTorch/XAI/Grad-CAM/Multi-label Classification/CheXpert/Generalization
Read more →

#05

About

Stack & Tools

Technologies and tools I use across product development, deployment, and maintenance.

Languages

  • Python
  • C++
  • Golang
  • SQL
  • Bash
  • JavaScript

Backend & Systems

  • FastAPI
  • Django REST Framework
  • REST APIs
  • Microservices
  • Distributed Systems
  • System Design
  • Data Structures & Algorithms
  • Operating Systems

AI & Machine Learning

  • PyTorch
  • TensorFlow
  • Transformers
  • OpenCV
  • NumPy
  • Pandas
  • OCR
  • LLM APIs

Infrastructure & Databases

  • PostgreSQL
  • Redis
  • Celery
  • Vector Databases
  • AWS EC2
  • AWS S3
  • Docker
  • CI/CD
  • Linux
  • Git

Credentials

Recognition

01
ACADEMIC2024

Amazon ML Summer School

Amazon · Invited cohort

Invited to Amazon's elite ML program covering deep learning, NLP, computer vision, and reinforcement learning — attended by top undergrads across India.

02
OPEN SOURCE2026

Google Summer of Code

BRL-CAD · Manifold subproject

Selected contributor improving C++ geometry processing CI reliability, benchmarking infrastructure, and cross-platform determinism checks.

03
AWARD2025

1st Place, Agentic AI Hackathon

Agentic AI Strategy Challenge

First place for designing a multi-agent automation system with workflow orchestration and real-time decision pipelines.

04
COMPETITIVE2024

3rd Place, Speed Coding

IIIT Surat · 100+ participants

Placed third in a timed competitive programming event against the full student body.

LeetCode

View Profile

Loading...

Less
More

#06

Get In Touch

Let’s build something useful.

Available for backend and systems internships, Summer 2026. Open to remote and hybrid roles.

EmailGitHubLinkedInRésumé

Currently at IIIT Surat · Mumbai, India · Open to remote and hybrid roles