Vince Jankovics, Machine Vision Developer in London, United Kingdom
Vince Jankovics

Machine Vision Developer in London, United Kingdom

Member since August 27, 2018
Vince is an engineer with expertise in machine learning and robotics. He has experience developing autonomous systems and artificial intelligence with emphasis on perception, decision making, and control. He is fluent in Python and C++ and has worked in a variety of projects as a consultant, helping clients achieve their goal.
Vince is now available for hire

Portfolio

Experience

  • C++, 5 years
  • Python, 4 years
  • Machine Learning, 4 years
  • Machine Vision, 4 years
  • Deep Learning, 3 years
  • Data Science, 3 years
  • Google Cloud Platform (GCP), 1 year
  • Kubernetes, 1 year

Location

London, United Kingdom

Availability

Part-time

Preferred Environment

Linux, Git, Spacemacs, Zsh

The most amazing...

...system I've developed is a generative machine learning model that turned simple sketches into pieces of art.

Employment

  • Research Visitor

    2019 - PRESENT
    City, University of London
    • Worked on neuro-symbolic learning for inductive logic programming problems.
    • Built on previously developed code, improving the performance and providing a Python interface for the C++ legacy code.
    Technologies: Machine Learning, C, C++, Python, Pytorch
  • Machine Learning Engineer

    2019 - PRESENT
    VAIC Ltd.
    • Worked on proof-of-concepts and feasibility studies for machine learning systems.
    • Worked on software engineering and DevOps for large scale cluster systems to support AI research.
    Technologies: Machine Learning, C, C++, Python, Pytorch, Kubernetes, GCP, AWS, Azure
  • Machine Learning Engineer

    2017 - 2019
    Cambridge Consultants
    • Worked on advanced machine learning systems to provide cutting-edge solutions to clients by improving and tailoring state-of-the-art algorithms from academic publications.
    • Developed deep learning models using Pytorch and Tensorflow.
    • Worked on data collection and preprocessing for imaging problems.
    • Developed models for time series and sensor data classification, using Boosted Trees and Neural Networks.
    • Deployed ML systems using C/C++.
    • Worked on data mining using Python.
    Technologies: Machine Learning, Python, C++, Pytorch, Tensorflow
  • Application Support Engineer

    2016 - 2017
    The MathWorks
    • Provided technical support for customers in various fields, e.g. robotics, control systems signal processing, embedded systems, and machine learning.
    • Worked on a drone simulation using C++, Matlab, and Simulink.
    • Worked on unit testing of new features for the deep learning toolbox.
    Technologies: Matlab, Simulink, C++
  • Robotics Intern

    2016 - 2016
    DroneX
    • Worked on software development, using C++ and ROS, to control a UAV platform.
    • Developed the control system, simulation and the mechanical test rig for a bipedal robotic system.
    • Worked on embedded software design for a real-time power management application on a low-cost microcontroller.
    Technologies: Python, C++, Embedded C
  • Student Research Assistant

    2013 - 2014
    University of Southern Denmark
    • Worked on the design of a tactile sensitive robotic fingertip and automated test framework for it in C++.
    • Developed a machine learning model for sensor characterization.
    Technologies: C++, Python

Experience

  • AI for Drug Discovery (Development)
    https://gtn.ai/

    I contributed to an industry disruptive startup that aims to solve drug discovery with AI. I worked on software engineering and DevOps for large scale cluster systems to support the research team, designed and implemented a system architecture that made experimentation more cost-efficient and much faster. Also, I proposed architectural changes to the research team in regards to generative models.

  • Financial Timeseries Prediction (Development)

    I worked on a proof of concept for a financial forecasting model that involved large amounts of unevenly spaced time series data. I developed a Pytorch data loader interface to an SQL data warehouse to efficiently train models at scale and tailored deep learning model.

  • AI Artist Demo (Development)
    https://www.cambridgeconsultants.com/vincent

    I worked on a machine learning technology demonstration that turned sketches into pieces of art. I built on top of cutting-edge deep learning architectures using generative adversarial networks to create a system that can hallucinate artistic paintings based on the input edges. I used Python with Tensorflow to build the architecture, implement the data pipeline and facilitate distributed training. Since the work that we've done for clients was confidential, this demo could showcase perfectly the capability of the team, and this demo, in particular, had a significant impact on our presence in the AI consulting domain.

  • Beyond Human Vision Demo (Development)
    https://www.cambridgeconsultants.com/deepray

    This technology demonstration aimed to reconstruct distorted images, so the model not only did pixelwise mapping, but it also had to fill in missing information based on the context. Generative adversarial networks are excellent in doing this, and it was shown how the model can change the output depending on the environment, I used Python with Pytorch for the training and a Flask back-end with a Typescript front-end for the deployed system.

  • Artificial Neural Network Based Adaptive Non-linear Control (Development)
    https://link.springer.com/chapter/10.1007/978-3-319-43488-9_9

    I worked on a non-linear controller that is able to learn the system dynamics that it controls. An artificial neural network is trained online to predict the system states to provide better performance than a simple PID algorithm. It was applied to a simple 2 degrees-of-freedom robotic arm to prove the concept. I developed the mechanics and the electronics for the prototype, simulated the dynamics in C++, and deployed the system to a low-cost Atmel microcontroller using Embedded C.

  • Humanoid Walking Robot (Development)
    https://irobotx.io/

    I developed system design for a humanoid walking robot, simulated and prototyped the control algorithm using Simulink. I implemented the Linux middleware for the actuators and sensors on the onboard controller.

  • IMAV 2017 Virtual Challenge (Development)
    http://www.imavs.org/2017/virtual-challenge.1.html

    I worked on the simulation environment for the IMAV drone competition. I used Gazebo, ROS, and Simulink to provide a high fidelity simulation that can be used to evaluate autonomous flight controllers.

Skills

  • Languages

    Python, C++, C, Bash, SQL
  • Frameworks

    Swagger, Flask, Boost, Spark
  • Libraries/APIs

    PyTorch, Sklearn, NumPy, Scikit-learn, TensorFlow, OpenCV
  • Platforms

    Linux, Docker, Kubernetes, Google Cloud Platform (GCP), Android, Amazon Web Services (AWS), Azure
  • Other

    Deep Learning, Robotics, Machine Vision, Machine Learning, Artificial Intelligence (AI), Generative Adversarial Networks (GANs), Google Cloud Platform, ROS, Condor, OOP Designs, Reinforcement Learning
  • Tools

    Zsh, Oh My Zsh, TensorBoard, Docker Compose
  • Paradigms

    Data Science, Agile
  • Storage

    MongoDB, Redis

Education

  • Master's degree in Robotics
    2015 - 2016
    University of Bristol - Bristol, England
  • Bachelor's degree in Mechatronics
    2012 - 2015
    University of Southern Denmark - Sonderborg, Denmark

To view more profiles

Join Toptal
I really like this profile
Share it with others