Aarush Agarwal

Fraud Detection: Developed a more robust buyer‑fraud detection system by implementing machine learning models with VertexAI and optimizing data pipelines with BigQuery and Dataflow. Improvements to data freshness and analysis increased predictive accuracy, while targeted feature selection significantly reduced training iteration time.

AI Agent Network: Built a distributed agent framework powered by Neo4j, where specialized AI agents collaborated through graph traversal queries. This enabled intelligent task decomposition and significantly improved the quality and efficiency of automated output. Patent filed.

Co-authored paper focused on spatial-partitioning a parallelized K-Nearest Neighbors algorithm, achieving up to a 200x speedup over FAISS (Facebook AI Similarity), Annoy (Spotify), and SCANN (Google) in low-dimensional (2-5) spaces.

Transitioned Python autograd and gradient functions to C++ and CUDA extension implementations and integrated with PyTorch JIT serialization, achieving a 10% decrease in KNN runtime.