Spaces:
Running
Running
Create a website for my resume using orange, dark gray, and white theme: Sovit Ranjan Rath sovitrath5@gmail.com — +91 9439678558 — DebuggerCafe.com — GitHub — LinkedIn Professional Summary Generative AI & Computer Vision Engineer with 2+ years of experience building multimodal AI systems (LLMs/VLMs, RAG) and 3 years experience in Deep Learning based computer vision. Authored 340+ technical articles and courses bridging cutting-edge research with real-world applications. Passionate about deploying generative AI to accelerate creative workflows in gaming. Core Skills • Generative AI: LLMs (Phi, Whisper), Vision-Language Models (CLIP, SAM), RAG Systems, Image Generation • Frameworks: PyTorch, TensorFlow, Hugging Face, LangChain, ONNX, Streamlit/Gradio • Technical Domains: Multimodal AI, Computer Vision, Model Optimization, Agentic Workflows • Deployment: Local AI systems, scalable pipelines, real-time applications • Collaboration: Cross-functional leadership (Product, Engineering, Research) Professional Experience Indegene — Lead SWE (GenAI & LLMs) — Apr 2025 – Present • Slashed API costs by 98.2% by optimizing in-memory context from 2M to 36k tokens. Architected an agentic workflow enabling code execution and dynamic UI visualization (graphs/charts) for healthcare solutions and built tools for real-time data interaction using generative AI. • Built MCP (Model Context Protocol) server for Excel reasoning integrated with GPT and Claude APIs, deployed internally across the organization. Converted existing FastAPI server archi- tecture to MCP server for enhanced AI agent capabilities. OpenCV University — Technical Lead, AI Education — Feb 2021 – Apr 2025 • Led development of 4+ courses on deep learning and computer vision, used by developers and engineers globally. Engineered multimodal RAG pipelines (text/vision/audio) and demo apps for CLIP-based semantic search and Whisper transcription. Collaborated with product/marketing teams to align AI education with industry needs. DebuggerCafe.com — Author & Consultant — 2020 – Present • Published 340+ tutorials on generative AI, RAG, and computer vision with reproducible code. Designed quantized CV models for low-compute environments and real-time video analysis pipelines. Key Projects • Multimodal AI Library: Integrated CLIP, SAM, and Molmo for NLP-guided image segmentation. • Local RAG System: Built a Python-based Q&A tool using Sentence Transformers + Phi and custom vector search. • Vision Transformers Library: Created pip-installable ViT/Swin/DETR implementations. • Object Detection Toolkit: Developed modular training scripts for Faster RCNN (PyTorch). Education B.Tech, Information Technology — 2016-2020 — CGPA: 8.61/10Technical Presence • 340+ Articles on LLMs, VLMs, generative AI, and deep learning (DebuggerCafe.com). • Open Source: GitHub repositories for RAG, vision transformers, and AI tools. - Initial Deployment
87121e8 verified | <html lang="en"> | |
| <head> | |
| <meta charset="UTF-8"> | |
| <meta name="viewport" content="width=device-width, initial-scale=1.0"> | |
| <title>Sovit Ranjan Rath - AI Engineer Resume</title> | |
| <script src="https://cdn.tailwindcss.com"></script> | |
| <link rel="stylesheet" href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/6.4.0/css/all.min.css"> | |
| <script> | |
| tailwind.config = { | |
| theme: { | |
| extend: { | |
| colors: { | |
| primary: '#FF7D33', | |
| dark: '#1A1A1A', | |
| light: '#F5F5F5' | |
| } | |
| } | |
| } | |
| } | |
| </script> | |
| <style> | |
| .section-divider { | |
| position: relative; | |
| height: 80px; | |
| overflow: hidden; | |
| } | |
| .section-divider svg { | |
| position: absolute; | |
| top: 0; | |
| left: 0; | |
| width: 100%; | |
| height: 100%; | |
| } | |
| .skill-badge { | |
| transition: all 0.3s ease; | |
| } | |
| .skill-badge:hover { | |
| transform: translateY(-3px); | |
| box-shadow: 0 10px 15px -3px rgba(0, 0, 0, 0.1); | |
| } | |
| .timeline-item:before { | |
| content: ''; | |
| position: absolute; | |
| left: -38px; | |
| top: 0; | |
| width: 16px; | |
| height: 16px; | |
| border-radius: 50%; | |
| background-color: #FF7D33; | |
| border: 3px solid #1A1A1A; | |
| } | |
| @media (max-width: 768px) { | |
| .timeline-item:before { | |
| left: -28px; | |
| } | |
| } | |
| </style> | |
| </head> | |
| <body class="bg-light text-dark font-sans"> | |
| <!-- Header Section --> | |
| <header class="bg-dark text-white py-12"> | |
| <div class="container mx-auto px-6 md:px-12 flex flex-col md:flex-row items-center"> | |
| <div class="md:w-1/2 mb-8 md:mb-0"> | |
| <h1 class="text-4xl md:text-5xl font-bold mb-2">Sovit Ranjan Rath</h1> | |
| <h2 class="text-2xl md:text-3xl text-primary font-semibold mb-4">Generative AI & Computer Vision Engineer</h2> | |
| <p class="text-lg mb-6">Bridging cutting-edge AI research with real-world applications through technical leadership and education.</p> | |
| <div class="flex flex-wrap gap-4"> | |
| <a href="mailto:sovitrath5@gmail.com" class="flex items-center text-white hover:text-primary transition"> | |
| <i class="fas fa-envelope mr-2"></i> sovitrath5@gmail.com | |
| </a> | |
| <a href="tel:+919439678558" class="flex items-center text-white hover:text-primary transition"> | |
| <i class="fas fa-phone mr-2"></i> +91 9439678558 | |
| </a> | |
| </div> | |
| </div> | |
| <div class="md:w-1/2 flex justify-center md:justify-end"> | |
| <div class="bg-primary p-1 rounded-full"> | |
| <div class="bg-dark p-1 rounded-full"> | |
| <img src="https://via.placeholder.com/250x250" alt="Profile Photo" class="rounded-full w-48 h-48 md:w-64 md:h-64 object-cover border-4 border-primary"> | |
| </div> | |
| </div> | |
| </div> | |
| </div> | |
| </header> | |
| <!-- Social Links --> | |
| <div class="bg-primary py-4"> | |
| <div class="container mx-auto px-6 md:px-12"> | |
| <div class="flex justify-center gap-6"> | |
| <a href="https://debuggercafe.com" target="_blank" class="text-white hover:text-dark transition transform hover:scale-110"> | |
| <i class="fas fa-globe text-2xl"></i> | |
| </a> | |
| <a href="https://github.com" target="_blank" class="text-white hover:text-dark transition transform hover:scale-110"> | |
| <i class="fab fa-github text-2xl"></i> | |
| </a> | |
| <a href="https://linkedin.com" target="_blank" class="text-white hover:text-dark transition transform hover:scale-110"> | |
| <i class="fab fa-linkedin-in text-2xl"></i> | |
| </a> | |
| </div> | |
| </div> | |
| </div> | |
| <!-- Main Content --> | |
| <main class="container mx-auto px-6 md:px-12 py-12"> | |
| <!-- Professional Summary --> | |
| <section class="mb-16"> | |
| <h2 class="text-3xl font-bold mb-6 relative inline-block"> | |
| <span class="relative z-10">Professional Summary</span> | |
| <span class="absolute bottom-0 left-0 w-full h-2 bg-primary opacity-30 z-0"></span> | |
| </h2> | |
| <div class="bg-white rounded-lg shadow-lg p-6"> | |
| <p class="text-lg leading-relaxed"> | |
| Generative AI & Computer Vision Engineer with 2+ years of experience building multimodal AI systems (LLMs/VLMs, RAG) and 3 years experience in Deep Learning based computer vision. Authored 340+ technical articles and courses bridging cutting-edge research with real-world applications. Passionate about deploying generative AI to accelerate creative workflows in gaming. | |
| </p> | |
| </div> | |
| </section> | |
| <!-- Core Skills --> | |
| <section class="mb-16"> | |
| <h2 class="text-3xl font-bold mb-6 relative inline-block"> | |
| <span class="relative z-10">Core Skills</span> | |
| <span class="absolute bottom-0 left-0 w-full h-2 bg-primary opacity-30 z-0"></span> | |
| </h2> | |
| <div class="grid grid-cols-1 md:grid-cols-2 lg:grid-cols-3 gap-4"> | |
| <!-- Skill Category 1 --> | |
| <div class="bg-white rounded-lg shadow-lg p-6"> | |
| <h3 class="text-xl font-semibold mb-4 text-primary">Generative AI</h3> | |
| <div class="flex flex-wrap gap-2"> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">LLMs (Phi, Whisper)</span> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">Vision-Language Models</span> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">RAG Systems</span> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">Image Generation</span> | |
| </div> | |
| </div> | |
| <!-- Skill Category 2 --> | |
| <div class="bg-white rounded-lg shadow-lg p-6"> | |
| <h3 class="text-xl font-semibold mb-4 text-primary">Frameworks</h3> | |
| <div class="flex flex-wrap gap-2"> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">PyTorch</span> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">TensorFlow</span> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">Hugging Face</span> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">LangChain</span> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">ONNX</span> | |
| </div> | |
| </div> | |
| <!-- Skill Category 3 --> | |
| <div class="bg-white rounded-lg shadow-lg p-6"> | |
| <h3 class="text-xl font-semibold mb-4 text-primary">Technical Domains</h3> | |
| <div class="flex flex-wrap gap-2"> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">Multimodal AI</span> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">Computer Vision</span> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">Model Optimization</span> | |
| <span class="skill-badge bg-dark text-white px-3 py-1 rounded-full text-sm">Agentic Workflows</span> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- Professional Experience --> | |
| <section class="mb-16"> | |
| <h2 class="text-3xl font-bold mb-6 relative inline-block"> | |
| <span class="relative z-10">Professional Experience</span> | |
| <span class="absolute bottom-0 left-0 w-full h-2 bg-primary opacity-30 z-0"></span> | |
| </h2> | |
| <div class="relative pl-12 border-l-2 border-primary"> | |
| <!-- Experience 1 --> | |
| <div class="timeline-item relative mb-10"> | |
| <div class="bg-white rounded-lg shadow-lg p-6"> | |
| <div class="flex flex-col md:flex-row justify-between mb-4"> | |
| <h3 class="text-xl font-bold">Indegene — Lead SWE (GenAI & LLMs)</h3> | |
| <span class="text-primary font-semibold">Apr 2025 – Present</span> | |
| </div> | |
| <ul class="list-disc pl-5 space-y-2"> | |
| <li>Slashed API costs by 98.2% by optimizing in-memory context from 2M to 36k tokens.</li> | |
| <li>Architected an agentic workflow enabling code execution and dynamic UI visualization (graphs/charts) for healthcare solutions.</li> | |
| <li>Built tools for real-time data interaction using generative AI.</li> | |
| <li>Built MCP (Model Context Protocol) server for Excel reasoning integrated with GPT and Claude APIs.</li> | |
| <li>Converted existing FastAPI server architecture to MCP server for enhanced AI agent capabilities.</li> | |
| </ul> | |
| </div> | |
| </div> | |
| <!-- Experience 2 --> | |
| <div class="timeline-item relative mb-10"> | |
| <div class="bg-white rounded-lg shadow-lg p-6"> | |
| <div class="flex flex-col md:flex-row justify-between mb-4"> | |
| <h3 class="text-xl font-bold">OpenCV University — Technical Lead, AI Education</h3> | |
| <span class="text-primary font-semibold">Feb 2021 – Apr 2025</span> | |
| </div> | |
| <ul class="list-disc pl-5 space-y-2"> | |
| <li>Led development of 4+ courses on deep learning and computer vision, used by developers and engineers globally.</li> | |
| <li>Engineered multimodal RAG pipelines (text/vision/audio) and demo apps for CLIP-based semantic search and Whisper transcription.</li> | |
| <li>Collaborated with product/marketing teams to align AI education with industry needs.</li> | |
| </ul> | |
| </div> | |
| </div> | |
| <!-- Experience 3 --> | |
| <div class="timeline-item relative"> | |
| <div class="bg-white rounded-lg shadow-lg p-6"> | |
| <div class="flex flex-col md:flex-row justify-between mb-4"> | |
| <h3 class="text-xl font-bold">DebuggerCafe.com — Author & Consultant</h3> | |
| <span class="text-primary font-semibold">2020 – Present</span> | |
| </div> | |
| <ul class="list-disc pl-5 space-y-2"> | |
| <li>Published 340+ tutorials on generative AI, RAG, and computer vision with reproducible code.</li> | |
| <li>Designed quantized CV models for low-compute environments and real-time video analysis pipelines.</li> | |
| </ul> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- Key Projects --> | |
| <section class="mb-16"> | |
| <h2 class="text-3xl font-bold mb-6 relative inline-block"> | |
| <span class="relative z-10">Key Projects</span> | |
| <span class="absolute bottom-0 left-0 w-full h-2 bg-primary opacity-30 z-0"></span> | |
| </h2> | |
| <div class="grid grid-cols-1 md:grid-cols-2 gap-6"> | |
| <!-- Project 1 --> | |
| <div class="bg-white rounded-lg shadow-lg overflow-hidden"> | |
| <div class="bg-primary text-white p-4"> | |
| <h3 class="text-xl font-bold">Multimodal AI Library</h3> | |
| </div> | |
| <div class="p-6"> | |
| <p>Integrated CLIP, SAM, and Molmo for NLP-guided image segmentation.</p> | |
| </div> | |
| </div> | |
| <!-- Project 2 --> | |
| <div class="bg-white rounded-lg shadow-lg overflow-hidden"> | |
| <div class="bg-primary text-white p-4"> | |
| <h3 class="text-xl font-bold">Local RAG System</h3> | |
| </div> | |
| <div class="p-6"> | |
| <p>Built a Python-based Q&A tool using Sentence Transformers + Phi and custom vector search.</p> | |
| </div> | |
| </div> | |
| <!-- Project 3 --> | |
| <div class="bg-white rounded-lg shadow-lg overflow-hidden"> | |
| <div class="bg-primary text-white p-4"> | |
| <h3 class="text-xl font-bold">Vision Transformers Library</h3> | |
| </div> | |
| <div class="p-6"> | |
| <p>Created pip-installable ViT/Swin/DETR implementations.</p> | |
| </div> | |
| </div> | |
| <!-- Project 4 --> | |
| <div class="bg-white rounded-lg shadow-lg overflow-hidden"> | |
| <div class="bg-primary text-white p-4"> | |
| <h3 class="text-xl font-bold">Object Detection Toolkit</h3> | |
| </div> | |
| <div class="p-6"> | |
| <p>Developed modular training scripts for Faster RCNN (PyTorch).</p> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- Education --> | |
| <section class="mb-16"> | |
| <h2 class="text-3xl font-bold mb-6 relative inline-block"> | |
| <span class="relative z-10">Education</span> | |
| <span class="absolute bottom-0 left-0 w-full h-2 bg-primary opacity-30 z-0"></span> | |
| </h2> | |
| <div class="bg-white rounded-lg shadow-lg p-6"> | |
| <div class="flex flex-col md:flex-row justify-between items-start md:items-center"> | |
| <div> | |
| <h3 class="text-xl font-bold">B.Tech, Information Technology</h3> | |
| <p class="text-gray-600">2016-2020</p> | |
| </div> | |
| <div class="mt-2 md:mt-0"> | |
| <span class="bg-primary text-white px-4 py-2 rounded-full font-semibold">CGPA: 8.61/10</span> | |
| </div> | |
| </div> | |
| </div> | |
| </section> | |
| <!-- Technical Presence --> | |
| <section> | |
| <h2 class="text-3xl font-bold mb-6 relative inline-block"> | |
| <span class="relative z-10">Technical Presence</span> | |
| <span class="absolute bottom-0 left-0 w-full h-2 bg-primary opacity-30 z-0"></span> | |
| </h2> | |
| <div class="bg-white rounded-lg shadow-lg p-6"> | |
| <ul class="list-disc pl-5 space-y-2"> | |
| <li>340+ Articles on LLMs, VLMs, generative AI, and deep learning (DebuggerCafe.com).</li> | |
| <li>Open Source: GitHub repositories for RAG, vision transformers, and AI tools.</li> | |
| </ul> | |
| </div> | |
| </section> | |
| </main> | |
| <!-- Footer --> | |
| <footer class="bg-dark text-white py-8"> | |
| <div class="container mx-auto px-6 md:px-12"> | |
| <div class="flex flex-col md:flex-row justify-between items-center"> | |
| <div class="mb-4 md:mb-0"> | |
| <h2 class="text-2xl font-bold">Sovit Ranjan Rath</h2> | |
| <p class="text-primary">Generative AI & Computer Vision Engineer</p> | |
| </div> | |
| <div class="flex space-x-6"> | |
| <a href="https://debuggercafe.com" target="_blank" class="text-white hover:text-primary transition"> | |
| <i class="fas fa-globe text-xl"></i> | |
| </a> | |
| <a href="https://github.com" target="_blank" class="text-white hover:text-primary transition"> | |
| <i class="fab fa-github text-xl"></i> | |
| </a> | |
| <a href="https://linkedin.com" target="_blank" class="text-white hover:text-primary transition"> | |
| <i class="fab fa-linkedin-in text-xl"></i> | |
| </a> | |
| </div> | |
| </div> | |
| <div class="mt-8 text-center text-gray-400"> | |
| <p>© 2023 Sovit Ranjan Rath. All rights reserved.</p> | |
| </div> | |
| </div> | |
| </footer> | |
| <script> | |
| // Simple animation for skill badges on scroll | |
| document.addEventListener('DOMContentLoaded', function() { | |
| const skillBadges = document.querySelectorAll('.skill-badge'); | |
| const observer = new IntersectionObserver((entries) => { | |
| entries.forEach(entry => { | |
| if (entry.isIntersecting) { | |
| entry.target.style.opacity = '1'; | |
| entry.target.style.transform = 'translateY(0)'; | |
| } | |
| }); | |
| }, { threshold: 0.1 }); | |
| skillBadges.forEach(badge => { | |
| badge.style.opacity = '0'; | |
| badge.style.transform = 'translateY(20px)'; | |
| badge.style.transition = 'opacity 0.5s ease, transform 0.5s ease'; | |
| observer.observe(badge); | |
| }); | |
| }); | |
| </script> | |
| <p style="border-radius: 8px; text-align: center; font-size: 12px; color: #fff; margin-top: 16px;position: fixed; left: 8px; bottom: 8px; z-index: 10; background: rgba(0, 0, 0, 0.8); padding: 4px 8px;">Made with <img src="https://enzostvs-deepsite.hf.space/logo.svg" alt="DeepSite Logo" style="width: 16px; height: 16px; vertical-align: middle;display:inline-block;margin-right:3px;filter:brightness(0) invert(1);"><a href="https://enzostvs-deepsite.hf.space" style="color: #fff;text-decoration: underline;" target="_blank" >DeepSite</a> - 🧬 <a href="https://enzostvs-deepsite.hf.space?remix=sovitrath/sovit-resume" style="color: #fff;text-decoration: underline;" target="_blank" >Remix</a></p></body> | |
| </html> |