ramenbuild ↗
My boutique AI agency for seed-stage founders — we help founders design and build agentic workflows that reason, retrieve, decide, and act across their users' real jobs. Workflow mapping before any code; ship an MVP, learn, iterate.
Anu Joy · Independent AI & data engineer
From prototype to production.
From prototype to production.
AI systems built to ship.
I work with founders and small teams to build production-grade AI systems — from the first prototype to a robust, deployable product.
01 · Experience
2021 — present
Sitespry
Built Sitespry — a RAG-powered document intelligence product. Ingests PDFs, Word, websites; generates semantic embeddings and auto Q&A pairs; provides hybrid vector search with citations; and deploys as embeddable chat widgets. Plugin architecture, MCP server integration.
Zango.ai
Consultant developer for core MVP of a regulatory intelligence platform. Built LLM-based horizon scanning for regulatory change detection, document analysis pipeline (PDF parsing, embeddings, semantic search), AI chatbot for policy Q&A, and compliance gap analysis.
Foundations
Geospatial analysis (OS OpenData), social network analysis, vector embeddings (HyDE) in browser-based ML, Firebase auth on Cloudflare Workers. Published as technical articles.
02 · What I build
AI & LLM systems
Chat, evals, classification, workflows.
Retrieval-augmented search
So your AI cites real sources.
Backend architecture
APIs, queues, auth.
Data pipelines
Ingestion, transformation, delivery.
Geospatial analysis
Mapping, spatial queries, OS data.
How I work
I care about correctness, legibility, and craft: systems that do what they say, fail gracefully (no silent breakages, no mystery errors), and are easy to reason about. I bring both the depth to architect complex pipelines and the pragmatism to ship things that work.
03 · Toolkit
PythonFastAPIPostgreSQLClaudeGeminiCohereVector DBsGCPCloudflareDocker
Have something to ship?
Taking on founders and small teams for AI, retrieval and data work.