Enrique Bruzual
Hi! I'm Enrique.
I’m a Principal AI Solutions Architect and Product Engineer with 30+ years of experience mastering software development, Python engineering, and privacy-first architectural systems. I am the founder of Zerikai, where I built the Zerikai AIO Scanner (in Beta soon) to engineer LLM-friendly markdown optimization and structure sites for AI-readiness. Additionally, I authored Zerikai Memory, an open-source local Python MCP server that implements tactical KV caching to drop enterprise LLM context costs by up to 50x. I continually bridge the gap between high-level AI strategy and deterministic, production-ready code to deliver exceptional, high-utility automation results.
REVIEWS FROM CLIENTS
zerikai_memory
Designed and shipped an open-source hybrid RAG architecture giving AI agents persistent, cost-ef...
zerikai_memory
Designed and shipped an open-source hybrid RAG architecture giving AI agents persistent, cost-efficient memory across sessions. Combines semantic vector search (ChromaDB), lexical re-ranking, Tree-Sitter AST-level code parsing, and a 4-step LLM auto-routing chain to return precise, source-cited retrievals without context re-injection overhead.
● Hybrid retrieval pipeline (semantic search plus lexical re-ranking) eliminates false-positive retrieval by treating each function as an atomic indexing unit via Tree-Sitter AST parsing across Python, JS/TS, HTML, CSS, and Markdown
● Agent context overhead reduced from approximately 40% of a 128K context window (raw file-chunk retrieval) to 1.6% via structured tool-result delivery, a 25x reduction that directly extends effective reasoning depth per session
● Full local mode (zero API cost, zero data egress) with ChromaDB vector storage and inline file:line source citations compatible with Cursor, VS Code, Claude Desktop, and pi.dev
KillShot -- Autonomous Lead Intelligence Pipeline
Designed and shipped an autonomous 4-stage AI lead qualificat...
KillShot -- Autonomous Lead Intelligence Pipeline
Designed and shipped an autonomous 4-stage AI lead qualification pipeline with full inference cost tracking and sub-500ms operator feedback.
AGENTIC PIPELINE & INFERENCE COST
● 4-stage qualification pipeline (summary generation, intent scoring, key point extraction, draft response) runs as a fully decoupled background system via Huey task queue, with per-request cost tracking and OpenAI-compatible LLM retry logic
● Inference cost managed per lead via explicit cost-per-request logging, enabling ROI measurement across qualification volume
● pgvector semantic search with 500ms debounce triggering enables intent-based lead discovery without additional inference calls or client-side state management
Multi-tenant SaaS platform automating Amazon seller financial operations across European marketplaces. The product was sunset followin...
Multi-tenant SaaS platform automating Amazon seller financial operations across European marketplaces. The product was sunset following the company'sparent company acquisition.
● Amazon SP-API integration engineered across financial reporting, KPI aggregation, and P&L analysis for four European brands, replacing manual spreadsheet workflows
● AWS KMS at-rest encryption implemented for all tenant credentials to enforce Amazon Data Protection Policy (DPP) compliance across a multi-tenant environment
● PostgreSQL token-bucket rate-limiting algorithm built to prevent SP-API 429 bans under burst traffic, protecting revenue-critical data pipelines
● Tenant isolation architecture designed using Django middleware with RBAC decorators, composite indexes, and automated PII redaction pipelines