Available — project-based work / Remote-first · Curaçao / Clients across NL / ~20 yrs shipping software
← Back to work
Laravel React AWS Bedrock pgvector

ASICS B2B Chat

Enterprise RAG assistant for developer support — secure, source-backed answers.

Role

Senior Full-Stack Engineer

Sector

Global enterprise

Challenge

A large enterprise needed to give developer partners fast, reliable technical answers without sending every query to a human. Generic chatbots weren't an option — answers had to be accurate, grounded in the company's own docs, traceable to a source, with enterprise-grade security.

What I did

Designed and built a production RAG assistant on AWS — secure ingestion/retrieval pipeline, vector search with pgvector, grounding and evaluation, multi-turn chat. Owned it end-to-end: architecture, the Laravel/React app, AWS infra, and the guardrails that keep an LLM trustworthy in production.

The solution

A secure, multi-turn assistant returning source-backed answers from the company's own knowledge base — the hard part of RAG, not just a demo.

Outcome

A production AI system trusted for real developer support in a global enterprise.

Stack
Laravel React AWS Bedrock pgvector Postgres Terraform
"Accurate, grounded in our own docs, traceable to a source — and secure enough for the enterprise."
Let's see if we're a fit

A free, no-pressure 20-minute call.

Tell me what you're building or what's stuck, and I'll be straight about whether I'm the right person.

Book your fit call
Hiring for a role? Freelance Laravel developer Freelance Python developer