José Serra, Computer Graphics Developer in Porto, Portugal
José Serra

Computer Graphics Developer in Porto, Portugal

Member since December 4, 2019
José has considerable experience decomposing complex problems into smaller manageable ones, primarily in the areas of computer graphics, Computer Vision, and machine learning. His solutions intertwine concepts from multiple fields to achieve comprehensible and straightforward solutions. Most of his work has focused on applying state-of-the-art approaches and tailoring them for the specified task.
José is now available for hire




Porto, Portugal



Preferred Environment

Python, C++, Dlib, OpenCV, MATLAB, PyCharm

The most amazing...

...project I've developed was an intelligent facial animation system designed to create unique character motion with minimal input from the author.


  • R&D Engineer

    2018 - 2019
    Industrial Light & Magic (London)
    • Worked on linear and non-linear optimization for character animation models.
    • Tasked with researching and implementing state-of-the-art research and tailoring it to the company's needs.
    • Created modular code using C++ and Boost that integrated into an existing pipeline.
    Technologies: Maya, Python, C++, Linear Optimization
  • Studio Engineer, Researcher

    2016 - 2018
    University of Bath
    • Worked to bridge research projects to industry applications, creating plugins and dealing non-linear optimization for facial animation.
    • Researched state-of-the-art approaches and reproduced them in laboratory conditions.
    • Wrapped existing research into applications that were user-friendly.
    • Tracked and fixed bugs, and implemented validation test suites.
    • Contributed to academic research and published papers pertaining character animation.
    Technologies: Visual Studio, Ceres, Unreal Engine 4, MATLAB, Maya, C++, Python
  • Software Developer

    2016 - 2016
    Mental Factory
    • Worked as a freelancer for Mental Factory, with the task of creating interactive applications for the Museum of Coin from Banco de Portugal.
    • Created a motion detection application to throw 3D objects based on the motion of the person.
    • Used facial detection and 3D depth estimation model to mint a coin with and individual's face.
    Technologies: OpenCV, Unity3D, C#
  • Teacher Assistant

    2015 - 2015
    University of Bath
    • Tutored at the laboratories for the course Advanced Computer Graphics, which dealt mainly with concepts related to rendering.
    • Responsible for grading student assignments.
    Technologies: OpenGL, C++


  • Is Anna OK

    I worked on capturing body and facial movements for Aardman BBC’s Is Anna OK? []. This was achieved using Vicon Shogun and Vicon’s Cara HMC. Within this project, I was also involved in the implementation of the tools used to drive the facial animation of the characters.
    For more information:

  • Bandai Namco: 11-11: Memories Retold

    Captured and previewed the motion for Aardman Bandai Namco’s 11-11 Memories Retold. We used Vicon Shogun to capture the motion of half of the actors and Unity to preview the retargeted motion.

  • Welsh National Opera Project: Rewind

    Captured the motion Karah Son for Rewind/Welsh National Opera’s Madame Butterfly project.
    We used Vicon Blade to capture facial and body motion.
    For more information, check CAMERA’s blog pos here [].

  • Semblance

    Internal collaboration (Co-Lab) between different departments of the University of Bath (CAMERA/CS department and The Edge) to create Semblance. We worked on the full project from inception to completion. The project itself takes the form of a VR dancing experience, where the dancer (captured used Vicon) drives an avatar in UE and leaves behind a ghostly trail.
    I worked on assembling the Vicon to the UE pipeline and implemented the UE experience.
    For more, information check CAMERA’s blog post and video here [].

  • Golem

    Helped develop a visual speech animation system for Golem and LIFEisGAME projects in collaboration with Microsoft’s MLDC in Lisbon. In this project, we implemented a modular speech animation framework that started with speech recognition to identify the phonemes and their timings, and then using a phone-to-viseme map; the animation was assembled and blended. We explored different phone-to-viseme maps and used MFCCs to vary the poses according to the intensity of the speech signal. The framework was also general enough so that different modules (text-to-speech, co-articulation) could be switched without affecting all the other steps required to generate the animation. This led to the iberSPECCH publication and my Master of science thesis.


  • Other

    Computer Vision, Visualization, Data Engineering, Optimization, Algorithms, Statistical Modeling, Research, 3D Animation, Computer Graphics, Pattern Recognition, 3D Visualization, Data Visualization, Artificial Intelligence (AI), Machine Learning, Character Animation, Statistical Data Analysis, Mathematics, Data Structures, Numerical Methods, Statistics, Statistical Methods, Clustering Algorithms, Data Analysis, Predictive Modeling, Artificial Neural Networks (ANN), Linear Optimization, Ceres, Autodesk Maya, Deep Neural Networks, Convolutional Neural Networks
  • Languages

    Python, C++, C#, Python 3
  • Frameworks

    Unreal Engine 4, Unity3D, Boost, Qt
  • Libraries/APIs

    OpenCV, NumPy, Eigen, PyTorch, Scikit-learn, OpenGL, Dlib
  • Tools

    MATLAB, Visual Studio, Jupyter, MATLAB Statistics & Machine Learning Toolbox, PyCharm, Maya
  • Paradigms

    Data Science
  • Platforms

    Windows, Linux


  • Ph.D. in Artificial Intelligence and Computer Graphics
    2011 - 2017
    University of Porto - Porto, Portugal
  • Master of Science Degree in Network and Information Systems Engineering
    2006 - 2011
    Faculty of Sciences, University of Porto - Porto, Portugal

To view more profiles

Join Toptal
Share it with others