πŸ’‘ Hello there! I am Parth

I am a passionate AI Software Developer with expertise in machine learning, deep learning, computer vision, and generative AI. My work focuses on creating innovative, data-driven solutions that optimize industrial processes and deliver real-world impact. From developing vision transformer architectures to deploying scalable AI models, I thrive at the intersection of cutting-edge technology and practical applications. Currently, at ISRA Vision GmbH (part of Atlas Copco), I build advanced AI solutions for industrial automation, leveraging tools like PyTorch, TensorFlow, and Kubernetes to drive efficiency and scalability.

πŸ–ΌοΈ Vision Transformer for Synthetic Data Generation

Leading a generative AI initiative at ISRA Vision:

  • 🎯 Vision: Developing vision transformer architectures for synthetic data generation
  • πŸ’‘ Innovation:
    • Implemented advanced deep learning models for data synthesis
    • Integrated rule-based decision agents for automated workflows
    • Reduced data acquisition costs by 30% through generative AI
  • 🌍 Impact:
    • Enabled scalable AI training with synthetic datasets
    • Streamlined industrial inspection processes
    • Enhanced model robustness for real-world applications

πŸš— Defect Detection for Car Surface Inspection

Spearheading an AI-driven quality control project at Atlas Copco:

  • 🎯 Vision: Enhancing car surface inspection through deep learning
  • πŸ’‘ Innovation:
    • Developed U-Net and ResNet-based models for defect detection
    • Incorporated adaptive gamma correction for image enhancement
    • Achieved 70% structural similarity index (SSIM) and 10% accuracy improvement
  • 🌍 Impact:
    • Reduced labor costs by 90% through automated inspection
    • Processed 800GB+ image datasets for precise 2D/3D mapping
    • Improved quality control efficiency in automotive manufacturing

πŸ“ Recent Blog Posts

πŸ–ΌοΈ Building a CLIP-like Model for Image-Text Alignment

Sharing insights on multimodal AI development:

  • 🎯 Vision: Guiding developers to build a CLIP-like model for image-text alignment
  • πŸ’‘ Innovation:
    • Step-by-step tutorial using PyTorch and Hugging Face transformers
    • Covers data preparation, model training, and evaluation for multimodal learning
    • Demonstrates practical implementation of vision-language models
  • 🌍 Impact:
    • Empowers developers to create AI systems bridging images and text
    • Enhances understanding of transformer-based architectures
    • Published on Medium, April 2025

🎯 Research Interests

AI and Machine Learning:

  • πŸ€– Deep Learning and Computer Vision
  • πŸ“Š Generative AI and Vision Transformers
  • πŸ”„ MLOps and Scalable AI Deployment
  • πŸ“ˆ Time Series Forecasting with Transformers

Industrial Applications:

  • 🏭 Industrial Automation and Quality Control
  • πŸ” Defect Detection and Image Processing
  • πŸ“‘ Large-Scale Data Processing
  • βš™οΈ Sustainable AI Optimization

πŸ† Recent Achievements

  • IEEE Publication (2023)
    • πŸ“š Published research on data-driven deep learning for Bitcoin price forecasting
    • πŸ“Š Leveraged transformer-based models for 22% accuracy improvement over ARIMA
  • Deutschlandstipendium Scholarship
    • 🌟 Awarded for academic excellence at Technical University of Darmstadt
    • πŸ“– Top performer in Information and Communication Engineering
  • TCS CodeVita Qualifier
    • πŸ’» Recognized for competitive programming and algorithmic problem-solving
    • 🧠 Demonstrated proficiency in data structures and algorithms

πŸŽ“ Education

  • M.Sc. in Information and Communication Engineering
    • πŸ›οΈ Technical University of Darmstadt (GPA: 2.0/5.0, ~3.5/4.0 equivalent)
    • 🌟 Deutschlandstipendium Holder
    • πŸ”¬ Relevant Coursework: Machine Learning, Deep Learning, Image Processing, Data Structures and Algorithms
  • B.Eng. in Electronics and Communication Engineering
    • πŸŽ“ Vishwakarma Government Engineering College, Ahmedabad (GPA: 8.8/10)
    • πŸ“‘ Focus: Signal Processing and Embedded Systems

πŸ’Ό Professional Experience

AI Software Developer, ISRA Vision GmbH (Atlas Copco), Germany (Oct 2023 – Jun 2025)

  • πŸš€ Develop vision transformer models for generative AI and industrial automation
  • πŸ’Ύ Deploy scalable AI solutions using Docker and Azure Kubernetes Service
  • ⚑ Optimize workflows with rule-based agentic systems, reducing costs by 30%

Software Development Engineer, Atlas Copco, Germany (Mar 2022 – Sep 2023)

  • πŸ–ΌοΈ Built U-Net and ResNet models for car surface defect detection, achieving 90% labor cost reduction
  • πŸ“Š Processed 800GB+ datasets for 2D/3D mapping and quality control
  • πŸ”§ Enhanced model accuracy by 10% with adaptive image processing techniques

Data Science Intern, Spryfox GmbH, Darmstadt (Oct 2021 – Mar 2022)

  • πŸ“ˆ Developed machine learning models (XGBoost, Logistic Regression) for pet disease prediction, improving accuracy by 20%
  • πŸ’» Engineered end-to-end data science pipeline with AWS deployment
  • πŸ” Conducted statistical analysis for customer spending insights

🎯 Teaching and Outreach

  • YouTube Content Creator
    • πŸŽ₯ Create educational content on machine learning, data science, and programming
    • πŸ‘₯ Community of 3.9k+ subscribers
    • πŸ“š Tutorials on Python, PyTorch, and deep learning applications
  • DAAD Student Representative
    • 🌍 Technical University of Darmstadt
    • 🀝 Led cross-cultural communications for 100+ international students
    • πŸ“… Organized tech-focused workshops and events

πŸ“š Current Learning Journey

Udemy Courses In Progress

Course NameInstructorProgressCertificate
End-to-End MLOps Bootcamp: Build, Deploy, and Automate ML with Data Science ProjectsKrish Naik40%πŸ”„ In Progress
Complete Guide to Building, Deploying, and Optimizing Generative AI with Langchain and HuggingfaceKrish Naik30%πŸ”„ In Progress