Hi, I'm Victor 👋

AI Architect & Director

Developer & Platform Experience · Moody's Analytics

17 years building production systems at scale, with the last three as AI Architect and now Director, owning the engineering platform that helps hundreds of developers build, ship, and operate software. My focus is AI infrastructure: RAG pipelines, LLM evaluation frameworks (Recall@k, groundedness, MRR), agentic workflows, and the cloud architecture that runs them in production. I hold a Master's in Data Science from UC Berkeley (GPA 3.81).

I host AI Builders: LatinX Edition, a podcast featuring researchers and practitioners shaping the future of AI, and teach RAG, embeddings, and LLM fundamentals at Techqueria workshops. I've spoken at Techqueria Tech Summit, Oakland Tech Week, and the Latino AI Summit.

See My Work View CV

What I Build

RAG Pipelines & Retrieval Systems

Production retrieval-augmented generation connecting LLMs to enterprise knowledge at scale

LLM Evaluation Frameworks

Rigorous benchmarking with Recall@k, Precision@k, MRR, and groundedness — not ad-hoc testing

Agentic Workflows

Multi-turn agent orchestration, function calling, and tool-use patterns deployed in production

Developer Platforms

Internal developer platforms and CI/CD infrastructure that help engineering teams ship faster

Featured Work

LLM Evaluation Framework
LLM Eval

Designed and operated the evaluation framework for generative AI products at enterprise scale. Defined retrieval quality metrics (Recall@k, Precision@k, MRR) and generation quality metrics (groundedness, faithfulness) — built on Databricks and Spark, adopted as standard practice across AI product teams.

RAG Pipeline Infrastructure
RAG

Architected production retrieval-augmented generation pipelines connecting LLMs to enterprise knowledge sources. Designed embedding workflows, vector search infrastructure, and retrieval optimization for production workloads at scale.

edge-ai-agent-lab — Live MCP Worker
Live · MCP

Live Cloudflare Worker implementing the Model Context Protocol (MCP) — exposes agentic tools at the edge using Workers AI bindings. A public reference implementation for MCP server patterns and edge AI deployment.

Speaking

Techqueria Tech Summit Oakland Tech Week Latino AI Summit

Writing

Introducing the RAG Evaluation Lab
RAG · LLM Eval

A practical guide to measuring retrieval quality in RAG systems — covering Recall@k, precision, and groundedness as the evaluation foundations every production AI system needs.

Demystifying Generative AI: My Journey with Techqueria Workshops
Teaching · GenAI

Behind the curriculum: how I designed hands-on AI workshops for the LatinX engineering community — from LLM fundamentals to production RAG systems and agentic architectures.

Introducing AI Builders: LatinX Edition
Community · Podcast

The story behind the podcast — why I started a show amplifying LatinX voices in AI and what I've learned from conversations with practitioners building at the frontier of generative AI.

All articles on Medium

LLM Evaluation Framework LLM Eval

RAG Pipeline Infrastructure RAG

edge-ai-agent-lab — Live MCP Worker Live · MCP

Introducing the RAG Evaluation Lab RAG · LLM Eval