Skip to content
View AlirezaAbedinii's full-sized avatar
1 follower · 0 following

Achievements

Achievement: YOLO

Achievements

Achievement: YOLO

Block or report AlirezaAbedinii

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
AlirezaAbedinii/README.md

🧑‍💻 About Me

  • 🎓 M.Sc. Computer Science from York University (Toronto, ON)
  • 🔬 Research Assistant at PACS Lab — building ML systems for the cloud
  • 🔭 Currently working on PRISM — Model-Family-Aware Partitioning and Multi-SLO Batching for Heterogeneous Serverless Inference
  • ⚙️ I work at the intersection of ML deployment, MLOps, and performance optimization — profiling-driven systems that cut inference cost and tame tail latency
  • 💬 Ask me about serverless inference, MLOps, AWS, autoscaling, and SLO-aware batching

🛠️ Tech Stack

Languages

Python JavaScript SQL Java C++ R Bash

ML / DL / LLM

PyTorch TensorFlow Keras ONNX scikit-learn NumPy Pandas

MLOps · Cloud · Observability

AWS Docker Kubernetes Prometheus Grafana Linux

Backend · Data · Tools

FastAPI Flask PostgreSQL MySQL ChromaDB Git


🤝 Connect With Me

LinkedIn Email

⭐️ Thanks for visiting — Alireza Abedini · Toronto, ON 🇨🇦

Pinned Loading

  1. rag-hybrid-search rag-hybrid-search Public

    Production-grade RAG service with hybrid (dense + BM25 + RRF + rerank) search, citation verification, and latency/cost instrumentation.

    Python

  2. JTank JTank Public

    Networked 2D tank battle game in Java (Swing): single-player campaign and real-time online multiplayer over client-server TCP sockets.

    Java

  3. MPHB-serverless-inference MPHB-serverless-inference Public

    Multi-SLO, partition-aware batching and provisioning for cost-efficient DNN inference on serverless platforms (built on HarmonyBatch and Gillis)

    Jupyter Notebook

  4. ImageCaptioning ImageCaptioning Public

    GAN-based image captioning on MS-COCO: a CNN encoder-decoder generator with an RNN discriminator, refined via Self-Critical Sequence Training (SCST). B.Sc. thesis implementing Chen et al., AAAI 2019.

    Jupyter Notebook

  5. Online-Shop Online-Shop Public

    A full-featured Flask e-commerce web app with a Persian (RTL) UI, featuring a customer storefront (search, filtering, cart, wallet checkout) and a complete admin dashboard for managing products, ca…

    JavaScript

  6. Trusted_Multi-View_Classification Trusted_Multi-View_Classification Public

    PyTorch implementation of Trusted Multi-View Classification (TMC, ICLR 2021): evidential deep learning that fuses multiple views with Dempster–Shafer theory to classify with calibrated uncertainty.

    Python