Collaborate on designing an adaptive gait model using machine learning and reinforcement learning.
Develop initial AI prototypes using real-time sensor data (joint angles, velocities, accelerations, and torques).
Experiment with deep learning models (e.g., LSTMs, Transformers, CNNs) to predict user intent and optimize robotic gait assistance.
Explore reinforcement learning algorithms for real-time adaptive control.
Leverage internal datasets and simulations to validate AI models before real-world implementation.
Review Trexo internal data, perform cleanup or restructuring as needed to ensure data integrity and effectiveness for AI model training.
Define and measure performance metrics, including interaction forces, user intent recognition accuracy, and user comfort.
Document and present findings clearly to technical and non-technical stakeholders.

Currently pursuing or recently completed a Master’s/PHD in Computer Science, Robotics, Biomedical Engineering, or a related field.
Experience with machine learning frameworks (e.g., TensorFlow, PyTorch).
Familiarity with deep learning architectures (RNN, LSTM, CNN) and/or reinforcement learning frameworks.
Familiarity with control theory and its robotics applications.
Proficiency in Python and comfort with software version control (e.g., Git).
Knowledge of medical devices or assistive technology.
Experience with biomechanics, gait analysis, or exoskeletons.
Strong analytical and problem-solving skills.
Familiarity in documenting requirements and creating comprehensive functional specifications.
Strong problem-solving skills and attention to detail.
Ability to work independently.
Excellent communication skills and the ability to explain complex technical concepts.
Strong critical thinking and analytical skills (able to piece together lots of information and condense it to something useful).

AI Robotics Intern

Key skills