The Early Mental Potential & Wellbeing Research Centre’s mission is to maximise every child’s mental and emotional capital by uplifting neurodevelopmental trajectories during early sensitive periods through interdisciplinary discovery science and translational technologies.

Toward this aim, we engage in 3 major activities and thrusts: 

1) Core Discovery Research, Empowering Science: Basic neuroscience research and advanced computational models to understand individual neurocognitive potential, developmental trajectories, and risk and resilience factors;
 
2) Translation to Clinic & Pedagogy, Empowering Practitioners: Developing precision assessment and intervention tools to optimise parent-child social and mental health within clinical, education and community settings;

3) Translation to Real-World Technologies, Empowering Families: Creating scalable solutions and real-world technologies for parents to enhance their child’s mental and cognitive wellbeing at home.

We are looking for a Computer Vision (Pose Estimation) engineer reporting to PI – Professor Victoria Leong, Assistant Professor Liu Ziwei and research teams on developing a fully automated end-to-end ML algorithm to estimate pose in dyadic sociometric measurements during parent-child interactions. This is a research collaboration aimed at yielding a larger data pipeline to predict trajectories for early childhood development.

Key Responsibilities:

• Designing, implementing, and optimizing pose estimation algorithms for various applications within our technology stack.

• Collaborating with hardware and software teams to integrate computer vision solutions into real-world systems.

• Conducting research to stay up-to-date with the latest advancements in computer vision and pose estimation.

• Analysing and enhancing the performance of existing pose estimation models through iterative testing and optimization.

• Working closely with data scientists and machine learning engineers to develop and train models using diverse datasets.

• Collaborating with the product team to understand and define the requirements for new features and functionalities related to pose estimation.

Job Requirements:

• Bachelor’s Degree in Computer Engineering, Computer Science, Electronics Engineering or equivalent.

• Strong background in machine learning and computer vision.

• Solid programming skills in languages such as Python, C++, or similar languages.

• Proficiency in using popular computer vision libraries and frameworks such as OpenCV, TensorFlow, PyTorch, Keras, etc.

• Strong understanding of 3D geometry, image processing, and machine learning techniques.

• Experience with integrating computer vision solutions into real-world applications and systems.

• Ability to work collaboratively in a fast-paced and innovative environment.

• Good command of English, both oral and written along with the ability to communicate effectively with a wide range of individual and professional groups.

• Proven work experience in 2D and 3D pose estimation, 3D pose recreation, and multiple camera system experience.

• Familiarity with GPU programming and parallel computing for efficient algorithm implementation.

• Research experience in relevant areas would be desirable (preferably worked in R&D sector with industrial experience in the project-related field).

• Ability to work with limited supervision and work collaboratively in a multidisciplinary team.

• Ability and willingness to work some flexible hours.

• Experience of working in a fast-paced commercial / industry setting is desirable.

Candidates with a proven track-record in one or more of these areas are welcome to apply. We will begin reviewing applications from Aug/Sep2024 onwards, until the position is filled, and regret to inform that only shortlisted candidates will be notified.

Hiring Institution: NTU