Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Skip to content
View vladimirrotariu's full-sized avatar
👋
👋
11 followers · 8 following

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx3Achievement: YOLO

Achievements

Achievement: QuickdrawAchievement: Pull Sharkx3Achievement: YOLO

Block or report vladimirrotariu

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.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

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

Report abuse
vladimirrotariu/README.md

Hola! 👋

About Me

I’m Vladimir — a passionate Mathematician and Physicist, now working as an AI & Backend Engineer focused on IoT and Digital Twins for Smart Cities.

My LinkedIn is Vladimir Rotariu.

What I Do

In my current role, I:

  • Preprocess IoT data with:

    • pandas/polars
    • numpy

  • Design and develop AI models for IoT data utilizing:

    • PyTorch
    • scikit-learn
    • statsmodels
    • optuna

  • Integrate these models into a FastAPI REST API

Interested in the AI project that I currently work on? Check out Proyecto GeDIA.

Publications

Focus Personal Projects

  • A FastAPI microservice the BLIP-large model from Hugging Face that is in charge of captioning user-uploaded images.
  • A Python package that leverages Apache Beam in order to efficiently orchestrate in-parallel Monte Carlo simulations.

Tech Stack (click on names to see relevant projects)

  • Programming Languages: Python, Java, C++, Rust, various dialects of SQL.
  • GCP Data Engineering Products Suite: Cloud Dataflow, Google BigQuery, Cloud Composer, Cloud Dataproc...
  • Main Frameworks: FastAPI, PyTorch, scikit-learn, statsmodels, Apache Beam.
  • Databases: PostgreSQL, Redis, SurrealDB, CrateDB, InfluxDB, MongoDB.
  • Tools: Jupyter Notebooks, Docker, Kubernetes, numpy, pandas, Eclipse Paho MQTT.
  • General knowledge: in web development acquired through personal projects and competitive bootcamps (React.js, Node.js, TypeScript, HTML, CSS, Solidity...)

Pinned Loading

  1. sponteen/high_quality_image_captioner sponteen/high_quality_image_captioner Public

    A FastAPI + Hugging Face app wrapping the BLIP large v1 image captioner

    Jupyter Notebook

  2. surrealml-vs-onnx-vs-pytorch surrealml-vs-onnx-vs-pytorch Public

    We will compare the performance of PyTorch with ONNX and SurrealML, a library designed for uploading and inferring using ML models directly inside a SurrealDB instance.

    Jupyter Notebook

  3. parallel-monte-carlo-simulations parallel-monte-carlo-simulations Public

    A package to orchestrate parallel (Monte Carlo) simulations via Apache Beam for an arbitrary number of models, with low-level parameter granularity, and flexible random number generator choice.

    Python 1

  4. spark-utility-classes spark-utility-classes Public

    A collection of utility classes and pocket apps that build on Apache Spark Java API

    Java

  5. dynamic-pricing-one-arm-bandit-crypto dynamic-pricing-one-arm-bandit-crypto Public

    A simple pricing of crypto one-arm bandit

    Jupyter Notebook