Enthusiastic and innovative, I am a professional deeply immersed in the world of Artificial Intelligence (AI) and Machine Learning (ML). My expertise extends to the realms of embeddings, Large Language Models (LLMs), generative AI, and Retrieval Augmented Generation (RAG). At the core of my skill set lies a proficiency in leveraging OpenAI APIs and the LangChain framework, allowing me to bring cutting-edge AI solutions to life. In my previous roles, I spearheaded ML model development and ensured seamless deployments on Nvidia's Triton inferencing server, optimizing GPU performance for multiple models without encountering Out-of-Memory issues. My commitment to efficiency is reflected in achieving the best response times. My technical versatility is showcased through proficiency in various programming languages, including Python, GoLang, Java, NodeJs, and Scala. I excel in designing and implementing micro-services, creating robust and scalable solutions. With a strong cloud computing background, I have successfully handled deployments on AWS Cloud, contributing to diverse features such as AWS RDS, notifications (SNS), message queues (SQS), Lambda, S3 integrations, and other AWS technologies. My meticulous approach ensures robust and secure cloud-based solutions. Beyond AI and ML, I bring a wealth of experience in mobile app development. Having worked on native Android apps and cross-platform mobile games in the past, I possess a holistic understanding of the mobile development landscape. I am passionate about pushing the boundaries of technology, and my professional journey reflects a commitment to continuous learning and staying at the forefront of emerging trends in the tech industry. As a dedicated professional, I am eager to contribute my skills to projects that demand creativity, technical excellence, and a forward-thinking approach. Let's connect and explore possibilities!