Postdoctoral Associate

MIT • Cambridge, MA

2d

About The Position

The 77 Lab in Mechanical Engineering is seeking a Postdoctoral Associate to conduct research at the intersection of computer vision, computer graphics, deep learning, digital health, and interactive simulation. The role involves developing AI-driven methods for video-based human movement analysis, focusing on sensing, pose estimation, skeleton-based learning, and implementation on mobile edge devices like smartphones and tablets for estimating clinical scores from patient videos. Additionally, the candidate will contribute to developing high-fidelity Unity-based simulation environments for human-in-the-loop experimentation, operator training, data generation, and multimodal system evaluation.

Requirements

• PhD in computer science, electrical engineering, mechanical engineering, biomedical engineering, robotics, computer graphics, or a related field at the time of hire.
• Strong track record of academic publications.
• Research experience in computer vision and machine learning, preferably including human pose estimation, video understanding, skeleton-based learning, spatiotemporal models, graph neural networks, transformers, or multimodal learning.
• Strong programming skills in Python and at least one systems-level or real-time programming language such as C, C++, or C#.
• Experience with modern deep-learning frameworks such as PyTorch or TensorFlow.
• Experience with Unity, real-time simulation, computer graphics, physics-based environments, 3D scene design, rendering, or game-engine development.
• Knowledge of Linux-based development, software architecture, system integration, and reproducible research workflows.
• Ability to work in a multidisciplinary research environment involving engineers, clinicians, postdoctoral associates, graduate students, and external collaborators.

Responsibilities

• Conduct research at the intersection of computer vision, computer graphics, deep learning, digital health, and interactive simulation.
• Develop AI-driven methods for video-based human movement analysis, with an emphasis on sensing, pose estimation, skeleton-based learning, and implementation on mobile edge devices such as smartphones and tablets for estimating clinical scores from patient videos.
• Contribute to the development of high-fidelity Unity-based simulation environments for human-in-the-loop experimentation, operator training, data generation, and multimodal system evaluation.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: Ph.D. or professional degree