Senior Software & AI Engineer · 14 years · Oviedo, Spain
Platform engineering meets applied AI — RAG/LLM systems, multi-tenant platforms, agent runtimes
Senior engineer with 14 years across software, embedded, and AI systems. I work at the intersection of platform engineering and applied AI — building the infrastructure that makes large systems and AI features reliable.
- Architecting a large-scale multi-tenant ERP at CTS KG — NestJS 11 · Angular · GraphQL · PostgreSQL · BullMQ
- Leading the AI workstream: built an MCP (Model Context Protocol) server exposing internal tools to AI agents, plus an embedded AI assistant
- Building RAG / LLM systems — citation-grounded responses, semantic caching, multi-provider orchestration, vector search
- Started in embedded — C/C++ on FreeRTOS — which still shapes how I think about latency, memory, and constraints in AI pipelines
- Portuguese (native) · English (fluent) · Spanish (intermediate)
ContractAI Review (portfolio) — RAG-based legal assistant where every answer carries mandatory citations, confidence scoring, and jurisdiction-aware reasoning. NestJS + pgvector + BullMQ; multi-provider LLM behind an adapter; document parsers behind a factory; semantic cache; per-tenant token budgets; encryption at rest; automated retention.
Zenth / ZenthOs (in progress) — multi-agent runtime: NestJS kernel + Python neural bridge for local embeddings. Sandboxed tool execution with tiered trust, protocol-first JSON Schema / OpenAPI contracts.
MCP server @ CTS KG — exposes internal ERP tools to AI agents via the Model Context Protocol.
TypeScript · NestJS · Angular · Node.js · Python · GraphQL · PostgreSQL · Redis · Docker · Ansible
AI/ML: RAG pipelines · embeddings · vector DBs (pgvector) · semantic caching · multi-provider LLM orchestration · MCP · agent runtimes
Earlier: C/C++ · FreeRTOS · embedded firmware
- Portfolio: https://yurilima.info
- LinkedIn: https://linkedin.com/in/yuri-matos-de-lima
- Email: [email protected]
Open to senior backend / full-stack (NestJS · Angular · Postgres) and AI/RAG/LLM engineering roles — remote, or hybrid in Madrid / Barcelona / Bilbao.