I am a versatile technology professional with over 7 years of experience, specializing in Python development, Machine Learning, Deep Learning, and Computer Vision. My background includes a Master’s degree in Computer Science and Telematics Engineering, providing a strong foundation across various fields from Full-stack Development to AI, MLOps, and real-time processing.
I have successfully deployed AI-powered solutions in the retail sector, leveraging my expertise in research and development, model deployment, and inferencing at the edge. My experience spans the entire machine learning lifecycle, from data preprocessing and model training to deployment, monitoring, and optimization on platforms like AWS and Databricks.
In addition to my technical expertise, I excel in managing scalable infrastructures with Docker and Linux, implementing CI/CD pipelines (e.g., Git/GitHub Actions), and integrating real-time AI models into production environments. My work includes diverse applications such as object detection, optical character recognition (OCR), and natural language processing (NLP), with a focus on driving impactful, data-driven solutions.
I spearheaded innovative projects focused on object detection and distributed systems, applying my expertise in machine learning, deep learning, and AI to solve complex challenges in the retail industry. I have developed and optimized end-to-end systems that enhance object detection accuracy and real-time processing capabilities. I utilize advanced techniques such as convolutional neural networks (CNNs) and transfer learning, in scalable, distributed AI pipelines using cloud platforms like AWS and Databricks.
Delivered comprehensive lectures and hands-on training in tech subjects like computer vision and natural language processing. Guided students through complex concepts and organized workshops to enhance their practical and theoretical knowledge. My role also involved assessing student progress and collaborating with colleagues to improve teaching methods.
Led the development of LUCIA, an innovative Autonomous Robotic System designed for efficient and accurate shelf auditing in retail environments. Leveraged AI and Computer Vision to enable real-time shelf analysis, optimizing inventory management and reducing human error.
Built an AI-powered LLM system to categorize and match products, improving search accuracy and recommendation quality through advanced text similarity, classification techniques, and prompting engineering.
Successfully integrated solutions to provide comprehensive client traffic insights and improve operational efficiency. Projects include:
Developed a computer vision system for self-checkouts automatically identifying fruits and vegetables, reducing manual input, checkout time, and thefts. Implemented image processing and machine learning techniques to enhance accuracy. Integrated with any checkout with a USB camera.
Designed and implemented a system for daily monitoring of network devices, focusing on camera surveillance. Developed algorithms to detect anomalies such as video loss, connectivity issues, and unsynchronized time. Implemented reporting mechanisms to promptly notify relevant personnel about detected anomalies.
Designed and implemented a machine learning-based recommendation system for checkout, suggesting relevant products based on real-time customer purchases during checkout, to enhance user experience and increase sales.
Enhance the capabilities of an AI model to engage in chat-like conversations that mimic human reasoning and understanding. This project focuses on creating conversational experiences on topics related to software development, data analysis, and artificial intelligence, enabling the AI to generate responses that resonate with human-like interaction.