Steve Leve
AI Engineering & Technical Leadership
Building Production AI Applications on Solid Foundations
I combine 25+ years of platform engineering expertise with modern AI capabilities to build systems that deliver real business value. From RAG architectures to edge computing, I engineer applications that are secure, scalable, and observable—not just prototypes that demo well.
What I Do
AI Application Development
Production-ready RAG systems, LLM integrations, and evaluation frameworks. I build AI applications that ship—with sub-second latency, streaming responses, and the instrumentation to know when something breaks.
Technical Leadership
Fractional CTO and advisory services for companies navigating technical complexity. Architecture decisions, team mentoring, and the strategic perspective that comes from building and scaling platforms over two decades.
Marketing Technology
Deep expertise in affiliate marketing, tracking systems, and revenue-critical MarTech infrastructure. 17 years building platforms that processed $1B+ in annual transactions.
Live Demos
See the work, not just the words.
Vercel RAG Demo
Production streaming chatbot with semantic search. Next.js 16, React 19, OpenAI GPT-4o, Neon PostgreSQL (pgvector). Sub-second responses across 100+ document corpus.
Visit Demo →Cloudflare Workers RAG Demo
Edge-deployed RAG with on-device LLM inference (Llama-3.1-8B). Zero external API calls, optimized for global latency. Built on Cloudflare Workers, Vectorize, D1, R2.
Visit Demo →Recent Work
Production RAG Systems
Shipped 4 RAG applications in December 2025, including the live demos above. Full-stack AI engineering across multiple platforms with custom evaluation frameworks.
Custom Evaluation Framework
Built metrics-driven RAG quality improvement using Precision@K, Recall, MRR, NDCG. Achieved +15% precision and +22% overall quality through systematic experimentation.
Fractional CTO Engagement
Providing technical leadership for a stealth MarTech startup, shipping beta product to early customers.
Let's Talk
I'm open to full-time roles, consulting engagements, and interesting problems worth solving.