🎉 Synthetic Data Generation for Edge-Case Object Detection
Threat actors are increasingly using AI to evade detection. We talk about a novel approach through using synthetic data for edge-case object detection tasks.
I am an experienced researcher and engineer specializing in machine learning, computational science, and security applications. With a background in computational chemistry and biophysics, I blend a deep understanding of scientific principles with cutting-edge technology to tackle complex challenges. I have worked extensively in AI, cloud infrastructure, and secure machine learning, driving impactful projects across sectors such as the financial industry, cybersecurity, and bioinformatics.
I am particularly passionate about applying machine learning to real-world problems, from developing scalable AI infrastructure to optimizing neural networks for deployment in resource-constrained environments. I have also contributed to open-source projects, focusing on the integration of reinforcement learning and retrieval-augmented generation (RAG) in small and large language model applications. I enjoy building secure and efficient solutions for threat detection in cybersecurity, with notable experience deploying large-scale inference models for enterprise security.
Throughout my career, I have been driven by a commitment to bridging the gap between research and practical implementation, making advanced AI and data science capabilities accessible to industry professionals.
PhD in Computational Chemical Physics (dropped out)
University of California Irvine
Master in Comp. Chemistry
Washington State University
BSc in Biology and Chemistry
Concordia University Irvine
I work at the intersection of software engineering and research. As an ML engineer at Microsoft Security Research, I blend engineering and research to enhance our security solutions. This website and blog reflect my personal views and should not be taken as representative of Microsoft. Here, I share insights on ML/AI, interpretability, and a wide range of other topics.
My goal is to uncover how advancements in AI/ML shape industries, drive innovation, and transform society, while ensuring their safe and responsible deployment.
Please reach out to collaborate 😃
Threat actors are increasingly using AI to evade detection. We talk about a novel approach through using synthetic data for edge-case object detection tasks.
Create a personal knowledge base and share your knowledge with your peers.
Use popular tools such as Plotly, Mermaid, and data frames.
Embed videos, podcasts, code, LaTeX math, and even test students!
Easily manage your projects - create ideation mind maps, Gantt charts, todo lists, and more!