Software Engineer · GenAI Platform · Arizona

Guadalupe HigueraI build agentic AI in production.

GenAI platform powering agentic systems for 10,000+ users at Wells Fargo. On the side, I ship LLM projects end to end: a fine-tuned race strategist, a Bedrock shopping agent, and a RAG engine that surfaces contradictions instead of hiding them.

See the projects View resume

live scenemove your cursor across it ·◇ hover the blue coyote ·◇ hover the red cardinal

// SELECTED_WORK

Three projects, one theme: agents that actually work.

All projects →

iRacing AI Race Strategist

Shipped

Eval score 29.7 → 78.5 · hallucinations 48/55 → 0/55 · 800–1100 ms end-to-end

Fine-tuned Llama 3.1 8B that calls race strategy in real time — and the eval harness that proved it works.

Llama 3.1 8B
QLoRA
transformers / peft
LM Studio
GGUF q4_k_m
Piper TTS

AWS Bedrock Agentic Shopping Assistant

Live

Live at shop.higuera.io · full AWS infra (Lambda, DynamoDB, API Gateway, S3, IAM) in Terraform

Autonomous shopping agent on AWS Bedrock — natural-language search, tool-calling, fully Terraform-provisioned.

AWS Bedrock Agents
Lambda
DynamoDB
API Gateway
S3
IAM

Titanic Historical RAG

Live

~40k chunks indexed · pairwise contradiction detection with 0–1 confidence + per-conflict rationale

A RAG search engine over the 1912 Titanic inquiries that surfaces contradictions between witnesses instead of hiding them.

OpenAI text-embedding-3-large
Pinecone
Claude Haiku 4.5
FastAPI
SQLite
pymupdf

▌ BUILDING

Production platform infrastructure for AI agents at Wells Fargo, powering five business use cases across policy, finance, and investments.

▌ STUDYING

MS in Computer Science at ASU — Knowledge Representation & Reasoning, Artificial Intelligence, Bio-Inspired Computing. Notes and reflections live on the blog.

▌ READING

Engineering books, papers, and the occasional historical primary source. Reviews and takeaways on the book reviews page.