Skip to content
View abedinia's full-sized avatar
🎯
Focusing
🎯
Focusing
128 followers · 121 following

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLOAchievement: Arctic Code Vault Contributor

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx2Achievement: YOLOAchievement: Arctic Code Vault Contributor

Highlights

  • Pro

Organizations

@snapp-cab

Block or report abedinia

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
abedinia/README.md

Aydin Abedinia

AI Platform & Backend Engineer · ML Systems · LLM Agents Former Lead, ML/MLOps & AI Platform @ Snapp! (50M+ users) · Ph.D. Researcher @ JD-ICE

I build AI platforms that ship — distributed systems, high-throughput microservices, and production ML in Go & Python. Currently bridging high-scale AI infrastructure and human-centered research through a Joint PhD across 🇮🇹 UniGe, 🇪🇸 UC3M, and 🇬🇧 QMUL.

🌍 Website • 💼 LinkedIn • ✉️ Email

🚀 Engineering

  • Lead, ML/MLOps & AI Platform @ Snapp! — built and ran an 11-engineer team; AI-driven dispatch serving ~20M real-time inferences/day at sub-50ms p99.
  • Expertise: Distributed systems, microservices, model serving, MLOps, feature stores.
  • Stack: Go, Python, Docker, Kubernetes.

🎓 Research

  • Focus: Human-centered AI, cognitive systems, semi-supervised learning.
  • Lab: ELIOS Lab, Università di Genova.
  • Publications: ICMLT 2025 (IEEE), IJMLC 2024 (Springer).

🧪 Key Projects

  • SemiCART — semi-supervised decision trees (+12% accuracy).
  • SemiDeep — distance-based weighting for deep learning.
  • NetExecGo — high-performance Go networking CLI.

Pinned Loading

  1. WeightedAI/semicart WeightedAI/semicart Public

    SemiCART is a semi-supervised decision tree algorithm that enhances traditional CART by leveraging unlabeled data in the training process.

    Python 9

  2. rust_decision_tree rust_decision_tree Public

    train a decision tree and make predictions in rust

    Rust 9

  3. WeightedAI/semideep WeightedAI/semideep Public

    SemiDeep helps your models focus on the right data, so they generalize better, especially when labels are scarce, noisy, or imbalanced.

    Python 11

  4. abedinia.github.io abedinia.github.io Public

    HTML

  5. NetExecGo NetExecGo Public

    NetExecGo is a Go-based command-line tool designed for executing commands through a specified socks proxy server.

    Go 2

  6. cartgo cartgo Public

    Cart implementation to fit predict load and save in Golang

    Go 1