I build AI systems and data platforms. 25 years across GIS, software engineering, cloud infrastructure, and applied AI — now shipping Dhi and LLM Governance Engine.
AI-powered fill-in-the-middle autocomplete for VS Code
PII firewall and YAML policy engine that stops sensitive data before it reaches any LLM
How I built an open-source PII firewall and governance policy engine for LLMs in a weekend — blocks sensitive data before it reaches GPT-4o, with YAML rules, audit trail, and webhook alerts.
How to add full repository intelligence to an AI IDE: multi-language Tree-sitter chunking (Go, Rust, Java, JavaScript), BM25 hybrid search with RRF, .gitignore-aware file discovery, and new /index-dir and /search API endpoints.
Step-by-step: build a < 150ms fill-in-the-middle autocomplete engine using Tree-sitter chunking, nomic-embed-text, Chroma, and StarCoder2-3B. Part 1 of building Dhi — the open-source AI coding IDE.
A deep-dive into designing a full AI coding IDE using only open-source components — FIM autocomplete, chat-in-editor, multi-file agents, repo understanding, and sandboxed code execution.
Explore the 5-step process of building LLMs: data curation, tokenization, Transformers, training at scale, and evaluation.
Audit and benchmark cloud vs. local LLMs with real-time PII scanning, GPU telemetry, and automated reports in this open-source governance platform.
Learn to deploy an EKS cluster on AWS using Terraform, GitHub Actions, and AWS services for a seamless CI/CD pipeline automation
Deploy AWS EKS cluster with eksctl: set up prerequisites, configure steps, and enable autoscaling for Kubernetes workloads
Compare Terraform's infrastructure provisioning to Helm's application deployment, and discover their complementary roles in cloud management
Explore the evolution from traditional data lakes to modern data lakehouses, and learn how this shift is revolutionizing big data storage with enhance
Deep technical posts — building in public, shipping open source, and lessons from production AI systems.