Ravi
Resume PDF
About Projects Case Studies Skills Open Source & Credentials Education Contact Resume PDF
Applied AI & Data Science @ IIT Jodhpur · CA Intermediate (ICAI)

Building intelligent systems that solve real problems.

I'm Ravi, an Applied AI and Data Science undergraduate at IIT Jodhpur (CGPA 8.75/10). I build AI-powered applications, agentic systems, retrieval pipelines, and deterministic software tools.

AI Engineering · Machine Learning · Open Source · Software Development

View Projects GitHub ↗ LinkedIn ↗ Download Resume (PDF)
Education
B.Sc. Applied AI & DS, IIT Jodhpur (CGPA 8.75/10)
Core Focus
Agentic AI, Hybrid RAG, Graph & Financial Systems
Verification
163+ Automated Pytest Checks & CI Workflows
Credentials
CA Intermediate · Anthropic & Harvard Programs
01 / About

Engineering approach

I am pursuing a B.Sc. in Applied AI and Data Science at IIT Jodhpur (Expected September 2029) alongside my CA Intermediate (ICAI) qualification. Combining computer science with formal accounting and auditing training shapes how I build software: probabilistic models should orchestrate workflows, while deterministic code enforces invariants.

Across my projects, that shows up in verifiable systems—backing an AI tutor with float64 NumPy invariants in ClaimLab, gating incident remediation behind GRAPH.COPY counterfactual sandboxes in AegisGraph, enforcing AST-allowlisted python -I -S sandboxes in StudyLab, and logging every valuation calculation into an immutable audit trail in FinMod-Agent.

I work across Python, TypeScript, SQL, FastAPI, React, FalkorDB, SQLite/PostgreSQL, Docker, and Rust, with an emphasis on automated testing and reproducible local setup.

Deterministic Verification Around LLMs

Enforcing numerical tolerances, AST sandboxes, and type-safe schemas in backend code rather than relying on prompt instructions.

Graph & Retrieval Grounding

Building hybrid sparse/dense retrieval and FalkorDB graph traversals that attach explicit citations and verifiable paths to every response.

Domain-Backed Financial Software

Translating corporate finance, DCF/WACC valuation, and auditing logic into structured, unit-tested APIs and interfaces.

02 / Featured Projects

Selected engineering systems

All Repositories ↗
ClaimLab interactive whiteboard and numerical experiment workspace 123 Offline + 2 Live Tests · CI Passing

ClaimLab

AI-Powered Teaching & Verified Numerical Learning System

Source-grounded teaching workstation coupling Meta's muse-spark-1.3 model with a transactional SVG whiteboard, three float64 NumPy labs, and sandboxed paper experiments.

  • LLM Orchestration: Epistemic tags ([Source], [Experiment], [Background]) and revisioned BoardPatch whiteboard state machine.
  • Verified Numerical Workflows: Softmax sensitivity, attention dimension scaling, and causal masking checked within 1e-10 scalar tolerance.
  • Adaptive Learning & Security: 2-variant mastery progression, HMAC-SHA256 tenant isolation, CSRF protection, and idempotency keys.
Python 3.12 FastAPI React 19 TypeScript NumPy pytest
GitHub ↗
WeMakeDevs × FalkorDB

AegisGraph

MCP-Native Graph Incident-Response Agent

Uses FalkorDB to trace what customer PII a CVE exposes across code, service mesh, and IAM roles—proves remediation safety in a counterfactual sandbox graph, then applies reversible fixes.

  • FalkorDB Graph Traversal: Variable-length Cypher queries across 9 node labels & 11 relationship types with HNSW vector + full-text anchoring.
  • Counterfactual Safety: Uses algo.betweenness, GRAPH.COPY, and algo.WCC to cut 6 PII paths to 0 while keeping 4/4 critical flows intact.
  • MCP Tool Guardrails: 13 stdio MCP tools protect critical services and record reversible ActionAudit mutations.
Python 3.12 FalkorDB Cypher MCP FastAPI React
3-Service Modular Architecture

StudyLab

Modular AI Learning & Research Platform

NotebookLM-inspired study platform for AI, data science, and finance learners—combining document ingestion, hybrid cited RAG, and isolated code-execution solving.

  • Hybrid RAG & Citations: Pairs sparse keyword scoring with dense retrieval, reranking, character-offset citations, and low-confidence rejection.
  • Isolated Code Execution: Runs Python solver snippets under AST allowlists and python -I -S with zero filesystem or network escapes.
  • Eval Harness Gate: run_eval.py enforces false_verified_rate = 0 across durable SQLite and Docker Compose services.
Python Hybrid RAG SQLite / Postgres AST Sandbox Docker Compose
GitHub ↗
40 / 40 Pytest Passing

FinMod-Agent (FMVA)

Financial Modeling & Valuation Engine

Deterministic valuation engine combining 500+ alias financial normalization, CAPM WACC, Gordon Growth & Exit Multiple DCF, comparable companies, and a 9-screen React UI.

  • Valuation Engines: Full UFCF DCF, live-beta CAPM WACC, peer multiples via yfinance, and Bear/Base/Bull scenarios.
  • Sensitivity & Audit Trails: 2D WACC × TGR matrices with monotonicity checks and immutable step-by-step calculation logs.
  • Exports & UI: Multi-sheet Excel workbooks, structured JSON API, and 9-screen Vite/React/Recharts workstation.
Python FastAPI Pydantic React Recharts yfinance
GitHub ↗

Additional Repositories

ProcureOps AI purchasing workspace

ProcureOps AI

Rust (Axum/Tokio) + Next.js + AG Grid procurement cockpit enforcing typed purchase mandates and PayPal Sandbox reconciliation.

Rust Next.js PayPal SDK
GitHub ↗

Leadforge Platform

Multi-user career acceleration platform on Cloudflare Workers, D1 SQLite, Drizzle ORM & React 19 with ATS resume builder and job scraper.

TypeScript Cloudflare D1 React 19
GitHub ↗

AyaWeightDoctor

Zero-gradient rank-1 weight surgery in Layer 16 of CohereLabs/tiny-aya-earth (3.35B), altering 0.6731% of weights in 0.02s to restore alignment.

PyTorch Safety Gradio
GitHub ↗

SQL Query Reviewer

OpenEnv RL environment (GRPO/PPO-ready) with shaped, deterministic per-step rewards across 20 production SQL correctness and security tasks.

Python OpenEnv RL Docker
GitHub ↗
03 / Architecture & Case Studies

Technical specifications

Inspect the problem framing, invariants, architecture, and test verification for each flagship project.

04 / Technical Skills

Categorized stack

Technologies demonstrated directly across shipped repositories and automated test suites.

Languages

Python SQL TypeScript JavaScript Rust

Used in ClaimLab, AegisGraph, FinMod-Agent, Leadforge, and ProcureOps AI.

AI / ML

NumPy Pandas SciPy Scikit-learn PyTorch LLMs

Float64 numerical recipes, rank-1 weight surgery, and statistical modeling.

AI Engineering

Hybrid RAG Embeddings Tool Calling MCP Agent Evaluation

13 stdio MCP tools in AegisGraph; sparse+dense retrieval & eval gates in StudyLab.

Backend & Databases

FastAPI REST APIs FalkorDB (Cypher) SQLite PostgreSQL Cloudflare D1

Graph topology + HNSW vector search, SQLite/Postgres migrations, and D1.

Frontend

React 19 Next.js Tailwind CSS Vite Recharts

Interactive SVG whiteboard in ClaimLab, 9-screen FMVA cockpit, and AG Grid ledger.

Engineering & Tooling

Git & GitHub GitHub Actions CI Docker pytest Cloudflare Workers

Automated CI workflows, multi-service Docker Compose, and deterministic tests.

05 / Open Source & Credentials

Pull requests & verified certifications

Open-Source Transparency

Owned Repositories vs. Upstream PRs

My flagship projects (ClaimLab, AegisGraph, StudyLab, FinMod-Agent) are published openly with setup guides, architectural documentation, and automated tests.

To state my record accurately: my current public pull request history consists of CI fixes, database migrations, and feature PRs within my own and hackathon repositories rather than third-party upstream repositories.

Upstream Goal: Actively expanding into direct contributions across established open-source AI and software engineering ecosystems.

Verifiable Pull Requests
Fix CI pytest collection by packaging server & inference
Hellinferno/Meta-hackathon #1
Merged / Closed
Day 15 hardening + B-19 fair-baseline trial harness
Hellinferno/nebious-Nvidia- #1
Closed
Add SerpApi company intelligence, cited research & diligence review
Hellinferno/Investment-banking-analyst- #1
Open
Fix CI database setup: index conflicts & PostgreSQL compatibility
Hellinferno/Micro-cfo #11 · #12 · #13
Open

Verified Certifications & Hackathons

Anthropic · Jul 2026

AI Fluency: Framework & Foundations

Credential ID: hfgjbcbbuieb
Anthropic · Jul 2026

Introduction to Claude Cowork

Credential ID: e9wrvx2bu8yw
Anthropic · Jul 2026

Claude 101

Credential ID: nrhjymrbxwic
Harvard University · Aspire Institute

Aspire Leaders Programme

Global Leadership & Analytical Cohort
IIT Guwahati · Jan 2026

Convolve 4.0 — A Pan-IIT AI/ML Hackathon

ID: 0587520d-e669-45e4-af1d-90ba7bd35a16
Kaggle (Google) · Dec 2025 & BCG · Oct 2025

5-Day AI Agents Intensive & BCG Strategy Simulation

Agent Architectures & Strategic Valuation
06 / Education

Academic background

LinkedIn Profile ↗
2025 — Expected September 2029 · CGPA: 8.75 / 10.0

Indian Institute of Technology (IIT) Jodhpur

B.Sc. in Applied AI and Data Science

Coursework and engineering focus across Machine Learning, Statistical Foundations, Numerical Optimization, Data Structures & Algorithms, and Retrieval Systems.

Applied AI Data Science Algorithms
2025 — Present · CA Foundation Cleared

Institute of Chartered Accountants of India (ICAI)

CA Intermediate Candidate

Training in Financial Reporting, Corporate Finance, Costing, Taxation Law, Auditing, and Regulatory Compliance—informing deterministic audit and valuation systems.

Financial Reporting Auditing Corporate Finance
07 / Contact & Resume

Get in touch

Open to open-source engineering collaborations, research roles, and AI/software engineering internships.

b25bs1273@iitj.ac.in
GitHub github.com/Hellinferno
↗
LinkedIn linkedin.com/in/raviiitcaintermidiate
↗
Web Resume Print-ready single-page CV
→