Arjaan Buijk, Machine Learning Developer in Plymouth, MI, United States
Arjaan Buijk

Machine Learning Developer in Plymouth, MI, United States

Member since December 19, 2017
Arjaan is a Python cloud developer and Rasa chatbot engineer with deep experience in web frameworks, APIs, machine learning, data science, and DevOps. He is also keen on several Python web frameworks like Django, Flask, and FastAPI, and he excels in a wide variety of Python libraries like Pandas, TensorFlow, and Rasa. Arjaan is a lifelong learner and seeks freelance clients to collaborate with on exciting and challenging projects.
Arjaan is now available for hire

Portfolio

  • Rasa
    TensorFlow, Ubuntu, Windows, DevOps, Pandas, GitHub, NumPy, Chatbots...
  • University of Colorado Boulder
    Ubuntu, Windows, Keras, GitHub, NumPy, Python, Slack, Zoom, Jira, Bitbucket...
  • MSC Software
    Qt, PyQt, Ubuntu, Windows, Microsoft Foundation Class Library (MFC), GUI...

Experience

Location

Plymouth, MI, United States

Availability

Part-time

Preferred Environment

Python, Django, Rasa, AWS

The most amazing...

...CI/CD pipeline I've recently developed is for a Rasa chatbot that fully automatically builds, trains, tests, and deploys to AWS S3, ECR, and EKS Kubernetes.

Employment

  • Solutions Engineer (NLP)

    2019 - 2021
    Rasa
    • Supported large enterprise customers by implementing and deploying mission-critical chatbots built with Rasa. Deployments use Docker, Docker Compose, Kubernetes, and OpenShift. Infrastructure a combination of on-prem, AWS, GCP, and Azure.
    • Designed and implemented NLU data, dialog stories, rules, forms, and custom actions (Python) for industry-relevant demonstrator chatbots.
    • Extended Rasa Open Source (Python) available at https://github.com/rasaHQ/rasa. This is an open-source machine learning framework to automate text- and voice-based conversations: NLU, dialogue management, connect to Slack, Facebook, and more.
    • Created and taught an online course on advanced deployment techniques with Kubernetes (https://www.udemy.com/course/rasa-advanced-deployment-workshop/).
    • Implemented Python Asyncio in back-end APIs resulting in dramatically improved throughput rates.
    • Created CI/CD pipeline that trains a Rasa bot, builds a custom docker image, stores the artifacts in AWS S3 and AWS ECR, automatically creates an AWS EKS cluster using the eksctl CLI, deploys Rasa with Helm, and Smoke Tests using Python.
    Technologies: TensorFlow, Ubuntu, Windows, DevOps, Pandas, GitHub, NumPy, Chatbots, Google Cloud Platform (GCP), Helm, Kubernetes, Docker, Python, Machine Learning, Natural Language Processing (NLP), AWS, CI/CD Pipelines, GitHub Actions, Rasa, CircleCI, Python Asyncio, PostgreSQL, Webhook, Webhooks, APIs
  • Freelance Data Scientist

    2018 - 2019
    University of Colorado Boulder
    • Developed a sequence-based machine learning model in Python using TensorFlow to predict university student application probability based on millions of time-stamped engagements.
    • Developed a clustering logic in Python using Scikit-learn to group students by engagement behaviors.
    • Built a decision tree model in Python using XGBoost to predict the probability for admitted students to enroll (yield).
    Technologies: Ubuntu, Windows, Keras, GitHub, NumPy, Python, Slack, Zoom, Jira, Bitbucket, SQL, MongoDB, AWS S3, Jupyter, Scikit-learn, XGBoost, TensorFlow, Machine Learning, AWS, APIs
  • Software Engineer

    1988 - 2019
    MSC Software
    • Developed a finite element and finite volume simulation software in Python, C++, and Fortran.
    • Designed and implemented a desktop application front-end with the Microsoft Foundation Class Library (MFC) and Qt.
    • Performed pre-sales demonstrations, customer training and support, sales, and business development.
    • Managed a team of solver developers. I was responsible for the definition and execution of projects, yearly employee reviews, and career planning of the direct reports.
    Technologies: Qt, PyQt, Ubuntu, Windows, Microsoft Foundation Class Library (MFC), GUI, Fortran, C++, Python
  • Founder | Owner

    2008 - 2014
    Simufact-Americas, LLC
    • Founded a company for the resale of manufacturing simulation software that I co-developed.
    • Achieved a 20-fold increase in revenue for the Americas region.
    • Used Python and web development to automate business processes.
    • Created pre-sales, sales, and post-sales onboarding processes.
    Technologies: Qt, PyQt, Fortran, Windows, Python, Django

Experience

  • Student Application Prediction

    I developed a data pipeline and a machine learning model to predict university student application probability based on time-stamped engagements.

    The data pipeline extracted millions of records from several SQL databases and generated features for the machine learning model. The end result of the data-pipeline was a pandas DataFrame written to an S3 bucket.

    The machine learning pipeline loaded the pandas DataFrame and trained a custom TensorFlow model used by the university admissions department to identify the most promising prospective applicants.

  • Financial Chatbot Starter Pack
    https://github.com/RasaHQ/financial-demo

    I designed and implemented NLU data, dialog stories, forms, and custom actions (Python) for a Rasa financial chatbot starter-pack.

    The implementation allowed the user to switch conversation contexts and receive guidance to succesfully complete conversations.

  • Rasa Advanced Deployment Workshop
    https://www.udemy.com/course/rasa-advanced-deployment-workshop/

    I created and taught a Rasa advanced deployment workshop, which is hosted on Udemy.

    The workshop teaches how to deploy a Rasa assistant on Kubernetes in the Google Cloud Platform (GCP) and how to use a CI/CD pipeline with GitHub Actions.

  • Chatbot for an Expert System

    I developed a chatbot with Rasa and Elasticsearch and deployed it to a single node Kubernetes cluster on AWS.

    The chatbot provides an alternative interface to a web-based expert system.

    The data pipeline creates word and sentence embeddings from web-scraped data and injects them into an Elasticsearch database. The embeddings are created using pre-trained machine learning models from TensorFlow Hub.

    The chatbot listens to questions from users and finds the most similar result by querying Elasticsearch.

  • Front-end Design and Implementation of a Windows Desktop Application
    https://www.mscsoftware.com/assets/2221_SF303ZZZLTDAT.pdf

    An industrially proven software package for the computer simulation of industrial forging processes. It combined a familiar and intuitive Windows graphical user interface with a robust solution procedure to provide unprecedented accuracy and speed in forging simulations.

    I was both a solver and a front-end developer.

  • Flask Catalog
    https://flask-catalog.herokuapp.com/

    This portfolio project demonstrates a Flask-based implementation of a secure user model with registration, email confirmation, reset, and login, combined with an example of a catalog of items grouped into categories.

    Registered users can CRUD the catalog via a web front end or via a REST API that adheres strictly to the JSON API 1.0 specification. The REST API supports advanced searching and filtering. End-to-end scenarios are demonstrated via a Python client written in a Jupyter notebook.

  • Use of Deep Learning to Clone Driving Behavior
    https://github.com/ArjaanBuijk/CarND_Behavioral_Cloning_P3/blob/master/README.md

    I developed a convolutional neural network regression in Python using Keras with a TensorFlow back end to drive a car virtually around a track. I improved on the well-known NVIDIA neural network for end-to-end deep learning for self-driving cars and achieved a 100% success rate on the most difficult track.

Skills

  • Languages

    Python, C++, SQL, Fortran
  • Libraries/APIs

    NumPy, Keras, Pandas, Microsoft Foundation Class Library (MFC), Scikit-learn, TensorFlow, Matplotlib, Python Asyncio, XGBoost, PyQt, OpenCV
  • Tools

    Rasa.ai, GitHub, Wingware IDE, Google Kubernetes Engine (GKE), Helm, GitLab, Amazon EKS, AWS CloudFormation, Jira, Jupyter, Bitbucket, Zoom, Slack, AWS Glue, CircleCI, Ansible
  • Platforms

    Docker, Jupyter Notebook, MacOS, Kubernetes, Ubuntu, Google Cloud Platform (GCP), Amazon Web Services (AWS), Heroku, Windows, Linux, AWS EC2, OpenShift
  • Other

    Chatbots, Natural Language Processing (NLP), GitKraken, AWS, Machine Learning, CI/CD Pipelines, Amazon Virtual Private Cloud, Sanic, APIs, Sanic Web Server, Rasa, GitHub Actions, TensorFlow Hub, GUI, FastAPI, Webhook, Webhooks
  • Paradigms

    DevOps, REST
  • Storage

    Elasticsearch, AWS S3, Google Cloud, Data Pipelines, MongoDB, PostgreSQL
  • Frameworks

    Qt, Flask, Django

Education

  • Master's degree in Aerospace Engineering (CFD)
    1982 - 1988
    Delft University of Technology - Delft, the Netherlands

Certifications

  • AWS Certified Cloud Practitioner
    AUGUST 2021 - AUGUST 2024
    Amazon Web Services
  • Nanodegree, Cloud DevOps Engineer
    MARCH 2021 - PRESENT
    Udacity
  • Google Kubernetes Engine
    JANUARY 2020 - PRESENT
    Google via Coursera
  • Deep Learning
    JANUARY 2019 - PRESENT
    Deeplearning.ai via Coursera
  • MongoDB for Developers
    SEPTEMBER 2018 - PRESENT
    MongoDB University
  • Nanodegree, Full-stack Web Development
    MAY 2018 - PRESENT
    Udacity
  • Nanodegree, Self-driving Car Engineer
    DECEMBER 2017 - PRESENT
    Udacity
  • Retrieving, Processing, and Visualizing Data with Python
    JANUARY 2016 - PRESENT
    Coursera

To view more profiles

Join Toptal
Share it with others