Saket Sultania
AI Engineer
About Me
Final-year B.Tech. Computer Engineering student at Mukesh Patel School of Technology Management & Engineering, specializing in AI and Machine Learning. Experienced in developing cutting-edge AI solutions, from facial recognition systems to legal assistance chatbots, through internships at Jio Platforms and Research fellowships. Proficient in Python, PyTorch, TensorFlow, and advanced ML techniques including RAG, PEFT, and LoRA. Passionate about leveraging AI to solve complex real-world problems, with a focus on NLP, computer vision, and ecosystem modeling. Seeking opportunities to contribute to groundbreaking AI projects and further my expertise in deep learning and generative AI. Committed to continuous learning and staying at the forefront of AI advancements.
Where I've Worked
AI & ML Engineer · People+ai
Architected core systems for knowledge graph generation and deployed an AI-powered digital form assistant, significantly improving data discovery and user efficiency.
Research Fellow · SimPPL
Investigated the effects of coordinated behavior on recommender systems, expanding simulation scope and conducting comprehensive evaluations on algorithmic vulnerabilities.
AI & ML Intern · Jio Platforms
Engineered a high-performance deep learning model for facial recognition quality assessment, achieving a 97% F1 Score and contributing to a comprehensive spoof detection dataset.
Programming Intern · GreenSat Innovation Labs
Engineered an automated API testing framework, significantly reducing manual effort and improving error detection efficiency.
Full Stack Developer · GenieGradz
Architected and implemented a comprehensive Learning Management System (LMS) using the MERN stack, showcasing end-to-end development skills.
Programming Intern · Plexian
Developed a high-performance Flask server API, integrating it with mobile and web applications to streamline data flow.
Artificial Intelligence Intern · SmartInternz
Crafted an intelligent chatbot leveraging IBM Watson Assistant and Discovery, integrated seamlessly into a Node-Red webpage.
Things I've Built
DermaVLM: Multi-modal Skin Disease Diagnosis
Engineered a ResNet101-based CNN to classify 20+ skin conditions with 92% accuracy and integrated it into a multi-stage VLM/RAG pipeline to generate diagnostic reports.
NyaayAI: RAG-Powered LLM for Legal Assistance
Built a RAG-powered legal assistant using ChromaDB and a fine-tuned LLM to accurately query legal documents, deployed with a Chainlit UI.
Publications
Get In Touch
I'm currently seeking new opportunities and my inbox is always open. Whether you have a question or just want to say hi, I'll do my best to get back to you!