I’m an AI Engineer passionate about building intelligent, scalable systems that bridge machine learning and real-world impact. I specialize in NLP, computer vision, and LLM-driven automation using Python, Hugging Face, LangChain, and cloud platforms like AWS and GCP.
I’ve engineered projects like GestureCap (gesture-based screen control using OpenCV), VocalVision AI (multilingual image captioning app), and LLM-powered financial analysis tools that automate insights from complex reports.
My focus is on delivering end-to-end AI solutions — from data pipelines and model deployment to intelligent automation — with measurable business outcomes.
I bring analytical thinking, fast learning, and hands-on problem-solving to every project. Let’s transform your ideas into intelligent systems.
Experience Level
Language
Work Experience
Education
Qualifications
Industry Experience
As the Research Author & AI Engineer, I published a paper on a GPT-based voice assistant integrating speech recognition, dialogue management, and NLP to enable real-time, context-aware conversational interaction. The assistant combines speech-to-text and LLMs to simulate natural human communication.
As the Data Analyst & NLP Engineer, I built an analytics dashboard that processes 10,000+ WhatsApp messages to uncover user activity, sentiment, and communication trends. Implemented with Python, Pandas, NLTK, Scikit-learn, Matplotlib, and Streamlit, it visualizes message density, emoji usage, and chat patterns through 10+ interactive plots.
As the Data Analyst & NLP Engineer, I built an analytics dashboard that processes 10,000+ WhatsApp messages to uncover user activity, sentiment, and communication trends. Implemented with Python, Pandas, NLTK, Scikit-learn, Matplotlib, and Streamlit, it visualizes message density, emoji usage, and chat patterns through 10+ interactive plots.
As the AI Engineer, I developed a Flask-based web application that generates image captions and translates them into 10+ international languages with text-to-speech (TTS) support. Using ViT-GPT2, MarianMT, and gTTS, the system delivers captions and audio responses with an average 1.2s latency, enhancing accessibility and multilingual communication.
As the AI Developer, I built a real-time gesture-controlled screen capture system using Python, OpenCV, MediaPipe, PyAutoGUI, and Tesseract OCR. The model tracks hand gestures at ~30 FPS and extracts on-screen text with ~90% OCR accuracy, eliminating manual inputs and enabling full automation of on-screen interactions.
Hire a AI Developer
We have the best ai developer experts on Twine. Hire a ai developer in Mumbai today.