I'm Gulshan Saini. I'm an AI/ML engineer with over 18 years of experience, specializing in Generative AI and Large Language Models. I currently work as the Associate Director of AI/ML Engineering at IntelloCore Pte Ltd.

You can find me on LinkedIn and X/Twitter.

I build and scale AI/ML solutions. My recent work involves fine-tuning LLMs, developing RAG chatbots, and creating multi-agent systems using tools like the OpenAI Assistants API. I'm passionate about optimizing AI performance; in the past, I've improved task completion rates by 40% and cut inference costs by 25%.

Currently, I'm exploring:

• Google's Gemini Pro
• Gemma for on-device applications
• Deploying AI models efficiently and privately

• Core Skills: Generative AI, LLMs, Fine-Tuning, RAG, NLP, Reinforcement Learning
• Technologies: Gemini Pro, Gemma, Vector Databases (Qdrant), Prompt Engineering
• Languages & Frameworks: Python, LangChain, Hugging Face, OpenAI API, Streamlit, Ollama
• Other Tools: Angular, NodeJS, MongoDB, REST APIs, Docker, AWS, Azure, GCP

• LLM Persona Finetuner: A project for fine-tuning LLMs with custom datasets to create specialized AI personas.
• RAG Chatbot Pro - AI Document Q&A: A private and secure RAG application that lets you chat with your PDF documents locally.
• Agent Testing Ground: A repository for experimenting with multi-agent AI systems.

I'm always open to collaborating on interesting AI/ML projects or mentoring those new to the field. Feel free to reach out on LinkedIn.