The Optics & Sensing Laboratory (OSLab) at the Max Planck Institute for Intelligent Systems in Tübingen (Germany) has an open position for a
Research Engineer (m/f/div)
for leading the development of the Non-verbal Interpersonal Communication Exploration (NICE) Toolbox.
We are supporting the development of highly realistic human and animal avatars for use in research, film, virtual reality, biology and medicine. Using unique 3D & 4D capture facilities, machine learning, computer vision and advanced graphics, we are modeling humans and animals shape and behavior. In the NICE Toolbox project, we build software for non computer scientists to support the exploration of non-verbal communication by detecting visual movements and behaviors of humans in videos. The aim is to foster better understanding of social interactions and communication patterns between people.
Roles & Responsibilities
We are looking for a research engineer to lead the development and extension of Non-verbal Interpersonal Synchrony Communication Exploration Toolbox. The candidate will work in collaboration with researchers from industry and engineers in computer vision. They are expected to have strong skills in software design and development as well as experience in computer vision and machine learning.

The candidate will be responsible for leading the following main project parts:

• Development, support, and application of open-source computer vision software toolbox:
• Extension of the aforementioned software for human-to-avatar communication, including creation of data assets and experiments for comparison and analysis
• Invest in existing and new collaborations with researchers and practitioners in psychology, psychotherapy, social machine learning, and related fields

Education & Experience

• Preferably PhD degree or MSc and strong academic background in the field of computer vision and machine learning
• Strong programming skills including but not limited to Python, CMake, OpenCV, PyTorch, Streamlit, and ReRun
• Experienced in deep learning frameworks
• Experienced with data acquisition from sensors (e.g., biofeedback, IMUs, pressure sensors, and eye-tracker)
• Experienced with software engineering methods and paradigms, including but not limited to continuous integration, unit tests, OOP, and git (e.g., issues, MRs, rebasing, code reviews)
• Good oral and written communication skills in English
• A natural team player and detailed-oriented perso

YOUR TASKS WILL BE TO:

• Maintain, extend, and test the developed software, e.g., using continuous integration (CI)
• Enhance body tracking, facial expression, gaze intersection algorithms
• Develop evaluation pipelines and tools in the field of computer vision and data processing
• Publishing open-source datasets and software tools available for the scientific community
• Develop novel capturing systems to record data on human-to-avatar communication
• Foster the development of communication quality analysis tools in collaborations with research and industry partners
• Oversee and support student assistants who are involved in this project
• Contribute to grant writing/application to expand and continue the project beyond the one year period

Education & Experience

• Preferably PhD degree or MSc and strong academic background in the field of computer vision and machine learning
• Strong programming skills including but not limited to Python, CMake, OpenCV, PyTorch, Streamlit, and ReRun
• Experienced in deep learning frameworks
• Experienced with data acquisition from sensors (e.g., biofeedback, IMUs, pressure sensors, and eye-tracker)
• Experienced with software engineering methods and paradigms, including but not limited to continuous integration, unit tests, OOP, and git (e.g., issues, MRs, rebasing, code reviews)
• Good oral and written communication skills in English
• A natural team player and detailed-oriented person

The candidate will be responsible for leading the following main project parts:

• Development, support, and application of open-source computer vision software toolbox:
• Extension of the aforementioned software for human-to-avatar communication, including creation of data assets and experiments for comparison and analysis
• Invest in existing and new collaborations with researchers and practitioners in psychology, psychotherapy, social machine learning, and related field