Skip to content
View JayR1031's full-sized avatar
💭
Building cross-lingual compliance evals — Algoverse Fall 2026
💭
Building cross-lingual compliance evals — Algoverse Fall 2026
43 followers · 285 following

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx2Achievement: QuickdrawAchievement: YOLO

Achievements

Achievement: Pair Extraordinairex3Achievement: Pull Sharkx2Achievement: QuickdrawAchievement: YOLO

Highlights

  • Pro

Block or report JayR1031

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.

Content in all repositories owned by your account will be closed.
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
JayR1031/README.md

Jay Rodriguez

I build and evaluate LLM systems for regulated industries, where a wrong answer has consequences — and I came to it from the customer's side of the table.

  • diGenius AI — AI Engineer. Zero-to-one enterprise AI platform: RAG over 3,000+ corporate records on LangChain + Azure AI Foundry, 500+ automated deployments.
  • Puente AI — Founder. Deployed trade-compliance RAG (LanceDB, Google Cloud Run) for the US–LATAM corridor; testbed for cross-lingual compliance evals.
  • Background — Supply-chain degree, six years selling compliance-driven products to regulated buyers.

Now: MS CS @ Northeastern (2027) · Algoverse AI Research, Fall 2026 — measuring how LLM compliance behavior fails across English, Spanish, and Portuguese.

Portfolio · LinkedIn

Pinned Loading

  1. multi-pdf-rag multi-pdf-rag Public

    Privacy-preserving multi-PDF RAG with fully local LLM inference (LangChain, ChromaDB). Precursor to the deployed Puente AI trade-compliance system.

    Jupyter Notebook 1

  2. CloudComputingMIA2025/team_awj CloudComputingMIA2025/team_awj Public

    PrivaSense MD

    Python 1

  3. reinforcement-language-model reinforcement-language-model Public

    Character n-gram language model with reinforcement learning from human feedback

    Jupyter Notebook 1

  4. graphical-models-intent-classification graphical-models-intent-classification Public

    Bayesian Network & Hidden Markov Model implementation for customer intent classification and text denoising | CS5100 AI Project

    Jupyter Notebook

  5. Unsupervised-News-Topic-Modeling Unsupervised-News-Topic-Modeling Public

    Unsupervised topic modeling and clustering (LDA) on real vs. fake news.

    Jupyter Notebook

  6. sms-spam-classification-nlp sms-spam-classification-nlp Public

    Comparative study of Naive Bayes and Logistic Regression for SMS spam detection using NLP techniques. Achieving 98% accuracy with rigorous feature engineering and ablation studies.