[{"data":1,"prerenderedAt":60},["ShallowReactive",2],{"project:/projects/deepscanner":3},{"_path":4,"_dir":5,"_draft":6,"_partial":6,"_locale":7,"title":8,"description":9,"tags":10,"live_url":16,"source_url":16,"image":17,"icon":18,"featured":19,"status":20,"role":21,"about":22,"stack":26,"milestones":31,"body":47,"_type":54,"_id":55,"_source":56,"_file":57,"_stem":58,"_extension":59},"/projects/deepscanner","projects",false,"","IBM DeepScanner","A scalable framework for detecting anomalies in LLM activations",[11,12,13,14,15],"Python","PyTorch","Ray","IBM Cloud","LLMs","#","https://placehold.co/600x400?text=IBM+DeepScanner","/icons/ibm.png",true,"Internal Tool","Research Engineer",[23,24,25],"DeepScanner is a scalable infrastructure designed to reverse-engineer foundation models by analyzing their internal activation states. It enables researchers to detect anomalous patterns—such as hallucinations or toxic outputs—before they manifest in the generated text.","I engineered the distributed workflow for this framework, optimizing the pipeline to run parallel experiments on the IBM Cloud Cognitive Cluster. This significantly reduced the time required to analyze large-scale models like Llama 3 and Granite.","The system supports modular probing of different model layers and integrates seamlessly with existing training pipelines, making it a critical tool for AI safety and interpretability research.",[11,12,27,28,29,30],"Ray (Distributed Computing)","IBM Cloud Cognitive Cluster","Hugging Face Transformers","Weights & Biases",[32,36,40,44],{"title":33,"date":34,"description":35},"Architecture Design","June 2025","Designed the modular architecture for extracting and analyzing model activations",{"title":37,"date":38,"description":39},"Distributed Pipeline","July 2025","Implemented Ray-based distributed processing to handle large-scale model data",{"title":41,"date":42,"description":43},"Optimization","August 2025","Optimized data loading and tensor processing, achieving a 3x speedup in analysis time",{"title":45,"date":42,"description":46},"Paper Submission","Results contributed to a non-archival paper later presented at the AAAI 2026 Workshop on New Frontiers in Information Retrieval",{"type":48,"children":49,"toc":50},"root",[],{"title":7,"searchDepth":51,"depth":52,"links":53},2,1,[],"markdown","content:projects:deepscanner.md","content","projects/deepscanner.md","projects/deepscanner","md",1786626763529]