Skip to content
View rahul0443's full-sized avatar

Highlights

  • Pro

Block or report rahul0443

Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
rahul0443/README.md

Rahul Muddhapuram

Software Development Engineer | Data Scientist | AI/ML Engineer
Email: rmuddhap@asu.edu | LinkedIn: linkedin.com/in/rahulmuddhapuram | GitHub: github.com/rahul0443


Executive Summary

Software Development Engineer and Data Scientist with a Master of Science in Data Science from Arizona State University (GPA: 3.83 / 4.0) and a Bachelor of Technology in Computer Science & Engineering (Artificial Intelligence and Machine Learning) from Malla Reddy University. Experienced in designing scalable distributed systems, microservices architectures, transactional data pipelines, and machine learning models. Proven background in building low-latency REST APIs, Redis rate limiters, transactional outbox implementations, graph streaming algorithms, and predictive ML models.


Education

  • Arizona State University (Tempe, AZ)
    Master of Science in Data Science, Analytics and Engineering | Aug 2024 - May 2026 | GPA: 3.83 / 4.0
    Coursework: Data Processing at Scale, Advanced Database Management Systems, Information Assurance and Security, Statistical Machine Learning.

  • Malla Reddy University (Hyderabad, India)
    Bachelor of Technology in Computer Science and Engineering (AI & ML) | Nov 2020 - May 2024 | GPA: 8.23 / 10
    Coursework: Data Structures and Algorithms, Operating Systems, Database Management Systems, Computer Networks, Software Testing, Full Stack Web Development, Machine Learning, Deep Learning, Natural Language Processing.


Core Technical Competencies

  • Software Development & Systems Architecture: Python, TypeScript, JavaScript, Java, C++, Go, Object-Oriented Design, Data Structures & Algorithms, REST APIs, Express, FastAPI, System Design.
  • Database Systems & Data Engineering: PostgreSQL, Prisma ORM, SQLAlchemy, Redis, DuckDB, Microsoft SQL Server (T-SQL), Apache Kafka, Kafka Connect, Neo4j Graph Data Science, Data Modeling, Transactional Outbox Pattern.
  • Machine Learning & AI Engineering: PyTorch, TensorFlow, LightGBM, Scikit-Learn, Optuna, LangGraph, Retrieval-Augmented Generation (RAG), Natural Language Processing (NLP), Computer Vision, Platt Scaling Calibration.
  • DevOps & Operational Excellence: Docker, Docker Compose, Kubernetes, Helm, GitHub Actions CI/CD, Prometheus Metrics, Health Probes, Jest, PyTest, Linux.

Featured Production Repositories

1. Continuity — AI Fault-Diagnosis & Knowledge-Capture Assistant

  • Target Focus: AI/ML Engineer / Forward-Deployed AI Engineer
  • Live Demo: continuity-bgf2.onrender.com
  • Repository: github.com/rahul0443/continuity
  • Highlights: RAG-based diagnostic assistant for semiconductor-manufacturing equipment faults, built with LangGraph, FastAPI, Gradio, and Chroma. Hybrid dense+BM25 retrieval over SOPs and incident logs; a LangGraph agent routes each query to a cited diagnosis or an escalation when retrieved evidence is insufficient, using Anthropic structured tool-use. Eval harness modeled on FAB-Bench (2026), a published RAG benchmark for semiconductor manufacturing — 4.97/5 mean score, 100% escalation accuracy across 16 scenarios.

2. TrustGuard Privacy Governance Platform

  • Target Focus: Software Development Engineer (SDE) / Security & Cloud SDE
  • Live Demo (real backend, not a mock): rahul0443.github.io/trustguard-privacy-platform — calls a deployed FastAPI service and returns a real server-computed HMAC-SHA256 signature per request.
  • Repository: github.com/rahul0443/trustguard-privacy-platform
  • Highlights: Data governance platform built with Python 3.12, FastAPI, Pydantic v2, and SQLAlchemy 2.0. Automated PII classification and redaction, Transactional Outbox dual-write guarantees, HMAC-SHA256 audit log signatures, PyTest suite with coverage, and a GitHub Actions CI/CD pipeline (lint, test, Docker build) gating every merge to main.

3. Audible Pulse Stream Engine

  • Target Focus: Software Development Engineer (SDE) / Distributed Systems
  • Interactive Demo (client-side simulation of the real logic): rahul0443.github.io/audible-pulse-stream-engine — the Express/Postgres/Redis backend runs in CI and Docker; it isn't hosted publicly since a free tier with managed Postgres+Redis isn't available the way it is for TrustGuard's SQLite-fallback service.
  • Repository: github.com/rahul0443/audible-pulse-stream-engine
  • Highlights: High-throughput audio stream entitlement and telemetry engine built with TypeScript, Express, PostgreSQL, Prisma ORM, and Redis. Atomic Redis-pipeline sliding-window rate limiter with in-memory fallback, idempotency key locks preventing duplicate licensing during network retries, Prometheus metrics, Jest test suite, and automated GitHub Actions CI/CD.

4. Portfolio Management Database Engine

  • Target Focus: Database Engineer / Backend Software Engineer
  • Repository: github.com/rahul0443/portfolio-management-system-db
  • Highlights: Relational database schema engineered in T-SQL for Microsoft SQL Server. Implements 9 relational tables with referential integrity constraints, 3 analytical views, multi-step transaction stored procedures (BuyStock), and automated audit triggers logging sector alterations into audit history tables.

5. Distributed Graph Streaming & Analytics Platform

  • Target Focus: Data Engineer / Distributed Systems
  • Repository: github.com/rahul0443/distributed-graph-streaming-platform
  • Highlights: Event-driven data streaming system ingesting NYC taxi trip events into a Neo4j Graph Data Science instance via Apache Kafka and Kafka Connect. Deployed on Kubernetes with Helm provisioning Kafka, ZooKeeper, and Neo4j nodes.

6. Brand Guardian AI Agentic Compliance Pipeline

  • Target Focus: AI/ML Engineer / LLM Systems
  • Repository: github.com/rahul0443/brand-guardian-ai
  • Highlights: Automated video advertising policy review engine using LangGraph DAG state workflows, GPT-4o, and vector RAG retrieval against policy documentation. Wrapped in a FastAPI service with Pydantic schema validation.

7. Credit Risk & Macroeconomic Stress Testing Platform

  • Target Focus: Data Scientist / Machine Learning Engineer
  • Repository: github.com/rahul0443/credit-risk-macroeconomic
  • Highlights: Machine learning modeling platform analyzing default risk across 1.37M LendingClub records and Federal Reserve Economic Data (FRED). Features a LightGBM classifier, Platt scaling probability calibration, and interactive macroeconomic scenario simulations.

Contact & Links

Pinned Loading

  1. brand-guardian-ai brand-guardian-ai Public

    AI-powered video ad compliance pipeline — automates FTC and YouTube policy review using GPT-4o, RAG, LangGraph, and Azure Video Indexer

    Python

  2. campaign-intel-hub campaign-intel-hub Public

    AI-powered marketing operations dashboard for campaign anomaly detection, health scoring, and optimization recommendations using GPT-4o.

    Python

  3. credit-card-churn-prediction credit-card-churn-prediction Public

    Credit Card Customer Churn Prediction and Behavioral Analysis using Random Forest & K-Means Clustering in Python.

    Jupyter Notebook

  4. pricing-analytics pricing-analytics Public

    End-to-end pricing analytics pipeline modeling gross-to-net optimizations, distributor discount structures, rebate ROI, and competitor gaps with interactive dashboard.

    Python