AI Directive Engineering
Design reasoning frameworks that keep AI systems stable. Directives are structured prompts plus governing rules—an algebra of allowed transformations that prevents drift, hallucination, and brittle failure modes.
Senior software engineer and AI systems architect with 10+ years of experience designing and building complex systems. Expertise in directive engineering, agent systems, and dimensional programming—a paradigm I developed that uses geometric manifolds as universal substrates for computation. Proven track record of building end-to-end platforms solo, from 3D game engines to AI routing systems. Seeking senior or staff role where I can apply structural rigor to make AI systems stable, deterministic, and efficient.
Design reasoning frameworks that keep AI systems stable. Directives are structured prompts plus governing rules—an algebra of allowed transformations that prevents drift, hallucination, and brittle failure modes.
Design agents whose job is to make other AI work better—verifier loops, evaluation harnesses, retrieval-augmented pipelines, and rule engines that catch what a single LLM call cannot.
Paradigm I developed using geometric manifolds as universal substrates. Identity-first programming, Russian Doll containment, Fibonacci scaling—mathematically grounded computation.
End-to-end platform development: frontend (WebGL2, vanilla JS), backend (Node.js, Python), infrastructure (VPS, CI/CD, nginx), databases (SQLite, PostgreSQL). Solo-built complete platforms.
WebGL2 rendering, 3D game platforms, procedural generation, real-time audio synthesis from manifold equations. Built 8+ games on a single substrate-driven rule engine.
Sovereign over rented: own the VPS, deploy pipeline, data model, directive doctrine. Vendor portability as first-class requirement. No primitive I cannot replace within one sprint.
JavaScript/TypeScript, Python, Java, .NET (C#), SQL, HTML/CSS, GLSL
WebGL2, Web Audio API, Node.js, Express, Three.js, React, GitHub Actions, Docker, nginx
LLM integration, prompt engineering, directive design, agent orchestration, RAG pipelines, vector databases, model routing, truth-table constraint engines
Linux (Ubuntu), VPS management, CI/CD pipelines, PM2 process management, rsync deploys, SQLite, PostgreSQL, nginx configuration
Manifold theory, differential geometry, TPMS (triply-periodic minimal surfaces), Fibonacci scaling, complex analysis, logarithmic spirals, optimization theory
Self-Employed / Portfolio Projects | 2020–Present
[Previous Employment] | [Dates]
All projects below are personal portfolio pieces—built end-to-end solo to demonstrate skills. None are commercial products or services for sale.
[Education details to be filled]
Route by regex pre-filter, truth-table constraints, decision-tree shortcuts, and Schwarz-D minimal-surface boundary so frontier credits go only where frontier reasoning is required.
Schema-validated outputs, retry budgets, verifier ensembles. LLMs never return free text to the next stage. Drift dies at the boundary.
No destructive updates. Every state is traceable through its lineage on the underlying manifold—debugging becomes walking the path, not guessing the past.
Own the VPS, deploy pipeline, data model, directive doctrine. Vendor portability as first-class requirement.
Available for full-time employment, open to remote. Seeking senior or staff role in AI systems architecture, software engineering, or related fields.