I design and ship production LLM infrastructure, graph analytics systems, and compliance-grade AI pipelines — then publish the internals.
I'm a Data Scientist / Data Engineer working at the intersection of large language models, graph analytics, and enterprise compliance. My day job involves building production AI systems on AWS infrastructure — the kind that need to be auditable, explainable, and robust under regulatory scrutiny.
My current focus is Project Kratos, an LLM-based multi-agent system built on AWS Bedrock, EKS, and Neo4j. Outside of that, I'm independently researching in-context learning theory and LLM quantization — writing papers I intend to publish on arXiv.
I write about the gap between ML research and production reality: what the papers don't tell you, what actually breaks at scale, and what's worth building from scratch.
Multi-agent LLM system on AWS. Orchestrates specialized agents across Neo4j knowledge graphs and Bedrock model inference for enterprise compliance workflows.
Streamlit tool converting Oracle SQL data quality rules into Great Expectations YAML. Handles compound queries, SSL proxy environments, and an 8-module rationalized architecture.
Neo4j-based fraud detection using community detection algorithms (Louvain, k-core, label propagation) and structural entropy for transaction network analysis.
110-control IT compliance framework with agentic 8-pass LLM extraction pipeline. Covers FDIC Part 370 and 12 CFR Part 330 with full regulatory basis mapping.
Spark streaming application for Kafka-based compound security event detection (password + address + card changes in same session) with YAML-driven pattern configuration.
Multi-pass relationship extraction system using Claude API with pronoun resolution and iterative refinement across unstructured text corpora.
Formalizes ICL success conditions: mutual information between prompt features and output correctness must exceed task entropy. Derives tractable bounds and empirical predictions.
Empirical study of memorization patterns across transformer layers using GPT-2 on A100 GPU. Identifies which layers disproportionately contribute to verbatim memorization.
Reimplementation and analysis of GPTQ on 7B-parameter models. Documents per-layer quantization error accumulation and accuracy/compression tradeoffs.
Context management strategy for multi-agent systems. The LLM gateway as foundational infrastructure — cost control, observability, rate limits, and model switching.
Agent ArchitectureHow graph entropy metrics catch money mule networks and synthetic identity fraud that rule-based systems miss entirely.
Graph AnalyticsBeyond the paper — practical implications of sparse subnetwork theory for fine-tuning, pruning, and deployment at scale.
ML TheoryA practitioner's view of FDIC Part 370, OCC standards, and the gaps between regulatory intent and actual AI system behavior.
Regulatory AIOpen to research collaborations, technical discussions, and consulting on LLM systems, graph analytics, or compliance AI in financial services.