Pearl Patel

Engineering smart AI so humans can do extraordinary things.

AI/ML + Software Engineer | Generative AI, Full Stack Development

β˜€οΈ About Me

Hi there! I’m a passionate AI/ML Engineer building scalable machine learning systems and generative AI applications that solve real-world problems.

πŸ’» Currently

Software Engineer @ Easley-Dunn | Working on backend systems, AI/ML projects, and scalable applications ✨

Based in Los Angeles, CA β­οΈπŸ™οΈ

🐚 Fun Facts

  • AWS DeepRacer Finalist 🏎️
  • Published with Springer πŸ“„
  • PyPI library with 2000+ downloads πŸ“¦

🌴 Professional Bits

  • AI/ML systems: NLP, Vision, Generative AI
  • Full-stack & distributed systems
  • Scalable, production-ready software

⛡️ Get in Touch

I’m always open to discussing AI, software engineering, or collaboration opportunities.

Email: pearl207@gmail.com | LinkedIn

πŸŽ“ Education

University of Southern California

Los Angeles, CA

Master of Science in Computer Science

June 2023 – December 2024

University of Mumbai

Mumbai, India

Bachelor of Engineering in Computer Engineering

August 2017 – June 2021

πŸ‘£ Experience

Easley-Dunn Productions, Inc. – Software Engineer

Los Angeles, CA | Feb 2025 – Present

  • Implemented backend systems and gameplay in Unity, integrating APIs and ensuring reliability across distributed components.
  • Led feature development and performance optimization, debugging critical issues to improve scalability of production systems.
  • Optimized memory usage and frame rates, ensuring a smoother user experience.

RiskSpan – AI Engineer Intern

Arlington, VA | Oct 2024 – Dec 2024

  • Built Generative AI models (GANs, VAEs) to create synthetic financial datasets, improving data diversity and model accuracy.
  • Optimized models via hyperparameter tuning, feature selection, and bias mitigation, improving predictive accuracy.
  • Developed ETL pipelines for preprocessing and validating financial datasets.

Reliance Jio – Software Development Engineer

Mumbai, India | Aug 2021 – May 2023

  • Performed thorough testing on mobile and web applications, collaborating with developers to improve usability.
  • Supported backend development of an internal data analytics tool.

IMT Atlantique – AI Research Intern

Nantes, France | Jun 2020 – Jul 2020

  • Developed RNN and LSTM-based prediction models for solar energy power production, reducing errors by 50%.
  • Find my work here

Blockchain & AI Lab, VJTI Mumbai – Research Intern

Mumbai, India | Nov 2019 – May 2020

  • Engineered Deepfake detection models using CNN-based architectures, improving accuracy.
  • Built efficient video data pipelines for high-dimensional inputs, improving detection performance.

πŸ–οΈ Side Quests

Check out all the cool projects I've worked on!

qtypi - Python Library for Quantum Computing Operations

  • Developed a Python library for quantum state and gate manipulations, including common and custom gates
  • Published on PyPI and developed on GitHub
Learn More

VisionTune AI

  • Developed a vision-language model to improve object count accuracy in text-to-image generation
  • Integrated Stable Diffusion with YOLOv8x for precise object detection and counting, and Low-Rank Adaptation (LoRA) for efficient fine-tuning in resource-constrained environments

Detecting and Mitigating Bias in Facial Recognition

  • Conducted comprehensive bias analysis in facial recognition models, primarily focusing on DeepFace and Viola Jones algorithms
  • Implemented a methodology to enhance DeepFace's comprehension of diverse female facial traits aiming to refine gender-specific facial interpretations and reduce observed biases

DeepRacer

  • Finalist for the AWS DeepRacer Women's League 2021
  • Developed a Reinforcement Learning based self-driving car racing agent using AWS DeepRacer
  • Adapted and iterated on Reinforcement Learning algorithms to optimize self-driving car racing performance, resulting in notable progress throughout the competition
Learn More

VCoins

  • Engineered a custom blockchain and cryptocurrency from the ground up, implementing innovative consensus mechanism for decentralized security
  • Architected and built out core cryptocurrency features including transaction processing, validation, and propagation across peer nodes
  • Established secure blockchain protocols enabling transparent and tamper-proof transaction ledgers

Sentiment Analysis on Text Feedback

  • Implemented advanced data preprocessing techniques, including text cleaning, tokenization, and feature engineering, to ensure optimal model performance
  • Designed a sentiment analysis system using Long Short Term Memory (LSTM) based Deep Neural Network to automatically analyze and classify user-generated text feedback
Learn More

Gesture Controlled Snake

  • Engineered a unique gaming experience by developing a gesture-controlled version of the classic Snake game
  • Utilized Python and Computer Vision techniques to develop a gesture recognition system, enabling intuitive control of the game character's movements through real-time analysis of player's gestures
Learn More

Contortion

  • Created an innovative Game using Unity
Learn More

πŸ“š Publications

You can find more on my Google Scholar

FileShare: A Blockchain and IPFS Framework for Secure File Sharing and Data Provenance

Khatal S., Rane J., Patel D., Patel P., Busnel Y.

Advances in Machine Learning and Computational Intelligence, Algorithms for Intelligent Systems (Springer), 2021

Issuing and Verifying University Certificates on Blockchain

Patel D., Rajan B., Mangnaik Y., Jain J., Mistry V., Patel P.

IC-BCT 2019, Blockchain Technologies (Springer), 2020

Blockchain In Depth

Kotha S, Patel P.

International Journal of Engineering and Computer Science (IJECS), 2020