Yaswanth Abhishek Varma
👋 About Me
Results-driven AI Engineer with hands-on experience in LLaMA 3.3, fine-tuning, Deep Learning, Natural Language Processing (NLP), and Machine Learning (ML), with a strong focus on building intelligent, multimodal AI applications.
I have successfully developed and deployed a range of advanced AI tools, including:
- Image Captioning System using PyTorch and Transformers for enhanced visual understanding
- Subtitle Generation App leveraging OpenAI's Whisper for multilingual transcription with time-aligned subtitles and PDF export
- AI-powered Multimodal Assistant integrating Gemini AI, gTTS, and OpenWeather API for real-time voice, chat, and weather interactions
I am skilled in designing intuitive user interfaces with Streamlit and deploying scalable, end-to-end AI workflows. Additionally, I have configured Ollama locally and connected it with Visual Studio Code, enabling seamless interaction with custom language models.
Passionate about creating real-time, accessible, and domain-specific AI solutions that bridge the gap between voice, vision, and language to deliver meaningful and impactful user experiences.
🚀 Featured Projects
🔗 Live Applications
- Image Captioning App - AI-powered image description generator
- Word to PDF Converter - Document conversion utility
- Object Detection System - Real-time object recognition
🛠 ️ Tech Stack & Tools
👨 💻 Programming Languages
🤖 AI/ML & Frameworks
🌐 Web Development
🗄 ️ Databases & Cloud
💻 Tools & Software
💼 Experience & Activities
🏢 Professional Experience
- Swecha Enthusiast: Actively participate in Swecha's medical camps and events, dedicated to social responsibility and community service
- App Development: Created multiple applications using Streamlit, demonstrating expertise in transforming ideas into functional, user-friendly programs
🏆 Key Activities & Achievements
- Web Development Foundation: Built a portfolio using HTML and CSS at an IIIT Hyderabad Bootcamp organized by Swecha
- Portfolio Showcase: Developed and showcased my portfolio website using HTML & CSS
- Current Project: Working on Electronic Health Records using React.js for frontend and Node.js as backend in Swecha
- Linux Expertise: Successfully executed complete system boot and installed Debian Linux distribution
- API Integration: Acquired API keys for accessing resources on AIMLand platform (OpenAI & ai.google.dev)
🌐 Specializations
- Machine Learning & AI: Deep Learning, NLP, Computer Vision, Model Fine-tuning
- Web Application Development: Full-stack development with modern frameworks
- Version Control: Proficient in Git, GitHub, and GitLab with CI/CD pipeline experience
- Networking: IP addressing, port management, device configuration, VLAN setup, TCP/IP/UDP protocols
- Project Management: End-to-end project lifecycle management and team collaboration
📊 GitLab Stats & Activity
🔥 Streak Stats
💻 GitLab Profile Stats
Note: Top languages is only a metric of the languages my public code consists of and doesn't reflect experience or skill level.
🎯 Current Focus
-
🔭 Currently working on Electronic Health Records using React.js and Node.js -
🌱 Learning advanced Large Language Model fine-tuning techniques -
👯 Looking to collaborate on AI/ML projects and open-source contributions -
🤔 Exploring multimodal AI applications and computer vision -
💬 Ask me about Python, AI/ML, Streamlit, Deep Learning -
📫 How to reach me: [email protected] -
⚡ Fun fact: I love bridging the gap between voice, vision, and language in AI!