Skip to content
View juan-casimiro's full-sized avatar
  • Sage Publications
  • London

Achievements

Achievement: Pull Shark

Achievements

Achievement: Pull Shark

Block or report juan-casimiro

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
juan-casimiro/README.md

Juan Casimiro

Senior Java backend engineer moving into AI Engineering. Two portfolio projects below — both built with a measure-before-optimizing discipline: every retrieval/generation decision is backed by an evaluation harness, including the negative results.

🔎 ai-research-assistant

RAG service — hybrid retrieval (dense + BM25 + cross-encoder reranking), grounded generation, provider-agnostic. 96.4% @ n=3, 98.2% @ n=8 on a 133-query golden QA evaluation harness. Repo →

🤖 ai-agent-module

LangGraph agent — classifies and routes questions across RAG lookup, calculation, and general-knowledge tools, with a self-correcting retry loop and conversation memory. Repo →

📍 London, UK · open to hybrid/in-office roles

Pinned Loading

  1. ai-agent-module ai-agent-module Public

    Stateful LangGraph agent routing questions across RAG, calculation, and general knowledge, with deterministic routing and self-correcting retrieval

    Python

  2. ai-research-assistant ai-research-assistant Public

    RAG Biomed service with hybrid retrieval and cross-encoder reranking, evaluated against a 133-query golden QA harness (96.4%/98.2%)

    Python