Skip to content
View PSaanviBhat's full-sized avatar
  • Bengaluru, Karnataka
  • 03:51 (UTC +05:30)
  • LinkedIn in/psaanvi

Highlights

  • Pro

Block or report PSaanviBhat

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

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

Report abuse
PSaanviBhat/README.md

P Saanvi

AI/ML Engineer | Computer Science Student | Explainable AI & Quantitative ML

Bengaluru, India | Email | GitHub | LinkedIn


Profile Summary

I am an undergraduate Computer Science student at PES University specializing in Artificial Intelligence and Machine Learning. I design and build high-performance, data-driven AI systems and quantitative pipelines that solve real-world problems. My experience spans sensor telemetry, time-series anomaly detection, explainable AI (XAI) and deep learning. I focus on constructing production-grade ML architectures, robust ETL systems, and low-latency inference modules.


Technical Stack

Languages


Python C JavaScript MATLAB Assembly
ML & Quant


PyTorch TensorFlow NumPy Pandas Scikit-Learn SciPy OpenCV
Systems & Ledger


Solidity PostgreSQL SQLite MongoDB Docker Arduino Pytest Power BI
Web & DevOps


React Node.js Flask Streamlit HTML5 CSS3 Tailwind CSS Git GitHub Linux

Projects Portfolio

graph TD
    classDef default fill:#0d1117,stroke:#30363d,stroke-width:1px,color:#c9d1d9;
    classDef highlight fill:#161b22,stroke:#58a6ff,stroke-width:2px,color:#58a6ff;
    
    Me[P Saanvi: Core Projects Portfolio]:::highlight
    
    Me --> DL[AI/ML & Deep Learning]
    Me --> Systems[Systems & Ledger]
    Me --> Quant[Quantitative Finance]
    
    DL --> P1["Explainable Smart Grid Fault Detection<br/>(VAE + DSPOT + XGBoost)"]
    DL --> P2["Spatio-Temporal Respiration Classifier<br/>(CNN-Conformer + InfoNCE Loss)"]
    DL --> P3["Memora Cognitive Assistive Platform<br/>(RAG + Biometric ArcFace/ECAPA)"]
    DL --> P4["Reinforcement Learning Traffic Optimizer<br/>(PPO + Reward Shaping)"]
    
    Systems --> P5["Clinical Trial Data Management<br/>(Private Permissioned PoA/DPoS Blockchain)"]
    Systems --> P6["Fault-Tolerant ETL Pipeline<br/>(Pandas Vectorization + Power BI)"]
    
    Quant --> P7["Option Pricing Suite<br/>(Black-Scholes-Merton + Monte Carlo)"]
Loading

GitHub Statistics

Core Developer Metrics Streaks & Language Breakdown
GitHub Stats GitHub Streak

Top Languages

Research Interests & Focus

  • Explainable AI (XAI) – Restoring interpretability in deep black-box models.
  • Quantitative Machine Learning – Appling statistical modeling and ML to financial markets and telemetry data.
  • Reinforcement Learning and Deep Learning – Sequential decision-making, game theory, and adaptive control systems.
  • Intelligent Edge Systems – Deploying low-latency ML and cryptographic verification to edge nodes/IoT devices.

Open to Collaboration

I am keen to collaborate on AI research, open-source ML systems, and quantitative modeling projects. If you are building in the ML/AI, Quant, or Decentralized Systems spaces, let's connect!

Email LinkedIn GitHub

Last updated: July 2026

Pinned Loading

  1. -SmartGridAnomalyDetection -SmartGridAnomalyDetection Public

    Forked from Dhruvjagadeesh/-SmartGridAnomalyDetection

    Jupyter Notebook

  2. civic-spark civic-spark Public

    Forked from soniaa27/civic-spark

    A modern, mobile-first civic engagement platform specifically designed for Bengaluru. Report, vote on, and track civic issues while earning XP, badges, and climbing leaderboards. Make Namma Bengalu…

    TypeScript

  3. Memora-AR-Based-Cognitive-Assistive-Platform Memora-AR-Based-Cognitive-Assistive-Platform Public

    Memora: AR-Based Cognitive Assistive Platform for Early Stage Alzheimer's Patients Integrating Facial Recognition, Age Progression Tolerance, Lifelong Learning, and Voice-Based NLP Prompts.

    Python 1

  4. Reinforcement-Learning-Intelligent-Traffic-Light-Controller Reinforcement-Learning-Intelligent-Traffic-Light-Controller Public

    Reinforcement Learning agent that learns to intelligently control a network of traffic lights in a simulated environment. The agent's goal is to minimize the average waiting time for cars and reduc…

    Jupyter Notebook 1