** R&D Section Head & AI Systems engineer ** I build the harness around the model — agent loops, context engineering, retrieval, tool access, and the eval infrastructure that decides whether any of it ships.
Full-stack engineer by background (10+ years of experince), which is exactly why my agents survive production — they're built like systems, not demos.
Career arc: Blockchain / Solidity ──▶ Cross-platform mobile (Flutter/cordova) ──▶ Full-stack (.NET / Angular / Node) ──▶ AI Systems
|
Plan → act → observe loops with bounded autonomy: budgets, stop conditions, checkpoint gates, and human-in-the-loop escalation. Adversarially reviewed before it's trusted. |
Deciding what the model sees on every call — system state, retrieved knowledge, tool definitions, memory. Most agent failures are context failures, and that's where I spend my token budget. |
|
Multi-provider, tiered / cascade routing optimized for cost-per-successful-task, not cost-per-token. |
Building Model Context Protocol servers and composable skills that give models governed access to real internal systems. Plumbing, not chatbots. |
|
Hybrid RAG over messy real-world documents; vector search (Qdrant, pgvector) alongside open, markdown-based knowledge graphs the agents can read and maintain. |
Golden sets from real inputs, regression suites, LLM-as-judge where it earns its keep. Observability without evals is just watching things break in higher resolution. |
| 💬 Languages |
|
| ⚙️ Backend |
|
| 🎨 Frontend |
|
| 🗄️ Data |
|
| ☁️ Cloud & DevOps |
|
