Senior Systems Engineer by title. Platform engineer, AI architect, and fullstack developer by practice. 20+ years turning infrastructure into systems that think, adapt, and ship. Currently orchestrating 16 AI agents across 19 repositories through a custom ops dashboard.
I started in operations — keeping servers alive, managing deployments, watching dashboards at 3 AM. That evolved into infrastructure automation, then into platform engineering, then into building the tools that build the tools.
Today I design interconnected systems where AI agents coordinate development work across an entire ecosystem. 16 specialized agents — each with scoped permissions, custom skills, and independent verification workflows — working in parallel across Python, TypeScript, C++, Go, and C# codebases. A custom ops dashboard tracks 95 backlog items, 15 epics, and 43 security findings.
The portfolio below isn't a collection of hobby projects. It's a self-aware development platform where the agents that build the software also audit, test, and document it. Every devlog entry is written by the agents that did the work.
Anonymized case studies from enterprise engineering work.
Migrated an entire engineering organization's codebase to a new Git org with GitHub Actions deployment pipelines. Built GitHub Apps integrations, implemented HashiCorp Vault with JWT authentication for secrets management, and integrated Artifactory for artifact storage. Automated dozens of operational processes including certificate provisioning via SecretStore.
Built a Star Trek LCARS-inspired GUI system for the engineering team featuring an integrated RAG-indexed codebase chatbot. Engineers search the entire codebase in natural language. Upgraded legacy Windows Forms to modern WPF, integrated with GitHub Actions and Artifactory. The dashboard became the team's primary interface for build monitoring, deployment tracking, and documentation search.
Not a buzzword list. Every item here has shipped in a real system.
Chat-driven AI art generation with TTS (55 voices including Fish Speech voice cloning), 22 visual themes, YouTube/Twitch media embedding, fair queuing, content safety pipeline, creator dashboard, and bouncing emotes. Live on Twitch. Debugged during actual streams.
Custom x86_64 kernel (C++) with from-scratch crypto (Curve25519, Ed25519, AES-GCM, ChaCha20-Poly1305), TLS 1.3, SSH/SFTP, NTFS filesystem, secrets vault, and GUI window manager. JefeRust is the companion Rust implementation exploring memory-safe systems programming.
RAG semantic search (ChromaDB), multi-model orchestration, D&D session archival pipeline (Ollama scene extraction, Gemini illustration, Fish Speech TTS, ChromaDB RAG indexing), MLflow experiment tracking, 3-tier LLM evaluation.
E2E encrypted messaging platform. AES-256-GCM encryption, RSA-4096 key exchange, WebSocket real-time, bot/webhook system. Four clients: React web, Tauri desktop, native Android (Kotlin/Compose), API.
Hardened Alpine-based Linux distro with 6-layer defense-in-depth. Reproducible ISO builds in under 8 minutes via Jenkins. 4 build variants, automated security auditing.
Three Twitch/Discord bots: Jefebot (30+ AI personalities, film club, Twitch commands), VibeBot4000 (DJ stream bot with shoutout queues), GygaxBot (D&D campaign management + AI session archival).
15+ HTML5 browser games, 3 satirical idle games, MMO prototype (MonoGame C#, .NET 8) with FFT job system and 101-test suite. 13 prototypes shipped in a single session using parallel AI agents.
19 repos. 16 agents. One interconnected platform.
RAG-powered assistant trained on my professional background. Searches a ChromaDB vector store with semantic retrieval. Try it.
38 documented sessions. Each one written by the agents that did the work, with independent security verification.
Added Kokoro TTS with 55 voices and voice cloning, expanded to 22 vibes, embedded Twitch streams, fixed four queue sync bugs during a live stream, shipped YouTube search, follower alerts, and emote rendering.
Six agents wrote their own sections. Built JefeHQ through 4 phases, hardened the kernel with 6 security fixes, expanded the agent roster from 5 to 11, and tracked 95 backlog items in a unified ops view.
3-tier LLM evaluation, knowledge distillation pipeline, embedding model upgrade, and a 900-line fine-tuning research doc targeting Qwen2.5-Coder-7B via Unsloth on RTX 5080.