AI Engineer with 3+ years production experience fine-tuning LLMs, and designing, deploying multimodal applications. Built systems processing real-world video/text data and helped startups integrate SOTA models into products. Seeking to deepen expertise in scalable LLM systems.

Fine-tuning models, building novel applications using SOTA multi-modal models, testing/evaluating LLMs, Designing AI workflows and open-ended agents.

Conducted research, developed prototypes, and automated workflows using state-of-the-art techniques and large language models (LLM) to enhance operational efficiency. Technologies used include Python frameworks, LLM, VLM, and prompt engineering.

As an AI Tutor at Remotasks' Coding Experts, I created challenging coding prompts to train AI models for code review and generation. I analyzed code samples and provided feedback to enhance model accuracy and efficiency.

A system that allows users to search for specific content within videos. It processes video content and creates searchable indexes, making it easy to find exact moments in long videos without watching them entirely.

Technologies used: gemini-flash api, embedding models, vector databases.

Implemented a autonomous AI agent, which can operate a computer using multi-modal models based on user defined tasks. Developed a api endpoint to use it as a UI testing agent.

GoogleAI SDK, pyautogui, EasyOCR, FlashAPI

Developed and documented a 'Neural Network from Scratch' project to deepen understanding of machine learning algorithms. The repository contains .ipynb and Python files with detailed study notes. Reviewed and synthesized insights from key research papers.

Designed a robust pipeline to generate high-quality mcqs using gemini-2.5-flash. Used the same model to evaluate the quality of generations according to custom rubrics. Reduced processing time and increased structured data reliablity to 99%+.

Technologies used: GoogleAI SDK, PostgreSQL, Pandas

An AI-powered tool that analyzes interview performances. It provides detailed feedback, helps identify strengths and areas for improvement, and offers a pass/fail assessment. Useful for job seekers practicing for interviews and for hiring managers in the recruitment process. Built using Gemini, Gradio. Deployed using Docker.

Relevant coursework: Digital Signal Processing, Computer Networks, Analog

and Digital Circuits, Operating Systems, Embedded systems, Artificial

Intelligence, and Machine Learning.

Relevant coursework: Physics, Chemistry, Maths and Electronics

Volunteered and managed cultural programs which were hosted.

Fluent English, Hindi and Kannada.

I love stumbling upon topics that let me dive into deep rabbit holes, Weight training, books and Football.