rafaelmelhem

Location: Brazil (São Paulo state)

Remote: Yes

Willing to relocate: Open to discussion

Technologies: Python, FastAPI, SQL, PostgreSQL, BigQuery, Elasticsearch, Neo4j, Docker, GCP, n8n, LLMs, RAG, Vector Search, REST APIs, ETL/ELT

Resume: linkedin.com/in/rafaelmelhem

Email: rafael.melhem [at] gmail

Applied AI Engineer / Data Generalist

I'm an engineer with 6+ years of experience working across AI (semantic search, vector databases, reranking), data analytics, data engineering, and software integrations, with a strong focus on solving real business problems and delivering production-ready solutions.

That happens with all products built on top of Open AI API. There are a few tricks to avoid this.

Cool! Will check it out thanks.

is GPTJ/NEOX good enough to generate code? tried it with SQL and it was really disappointing

I did something similar to it for my own use. Using natural language it make sql queries to your .csv, xlsx (soon I'll add features so you can connect to databases). but it is not mature enough to sell as a service. Feel free to reach me info [at] rafaelmelhem . com if you want and I send a demo :)

Would Thorium be part of that list as well?

Edit: I kinda know that because I have some weird passion about the elements of periodic table and because I'm reading "Periodic Tales: A Cultural History of The Elements From Arsenic To Zinc" which I really recommend!