As a passionate and dedicated Machine Learning Engineer, I specialize in Vision-Language Models (VLM) and diffusion models to address complex visual and textual data problems. My work revolves around leveraging state-of-the-art techniques in VLM to generate high-quality data, which fuels the creation of open vocabulary VLM detection models. These models are instrumental in generating pseudo labels, facilitating the training of compact and efficient models optimized for deployment on edge devices.With a strong foundation in machine learning and computer vision, I am adept at implementing advanced algorithms to push the boundaries of AI research. My current projects involve using and finetuning large language models (LLM) and diffusion models to synthesize data, ensuring robust and versatile solutions across various applications.In addition to my research, I have a keen interest in MLOps and DevOps. I am proficient in setting up and maintaining end-to-end machine learning pipelines using MLflow, which streamlines the process from model development to deployment. This integration ensures a seamless and efficient workflow, enabling the rapid iteration and deployment of models in production environments.I am driven by the potential of AI to transform industries and am committed to contributing to advancements in computer vision and AI technologies. Connect with me to discuss collaborations and innovations in this exciting field.