25% off

Applykite25

Publisher
source

Charalambos Poullis

1 week ago

PhD Position: Intelligent AI Systems for Surgical Operations (IASO) – Computer Vision, Deep Learning, and Robotics Concordia University in Canada

I am recruiting a PhD student for research in AI-driven surgical robotics, computer vision, and 3D reconstruction at Concordia University.

Concordia University

Canada

email-of-the@publisher.com

Invalid date

Keywords

Computer Science
Electrical Engineering
Medical Imaging
Deep Learning
Virtual Reality
Computer Vision
Surgical Robotics
Augmented Reality
Artificial Neural Network
Sensor Fusion
Computer Graphics
Robotics
Gpu Acceleration
3d Reconstruction

Description

The IASO (Intelligent AI Systems for Surgical Operations) project at Concordia University, in partnership with THINK Surgical and funded by NSERC Alliance, is seeking a PhD student to advance real-time sensing and spatial intelligence for robotic surgical systems. Building on the ACESO project's breakthroughs in camera calibration and tracking, IASO integrates deep learning, computer vision, and multi-sensor fusion to achieve sub-millimetric accuracy in 3D reconstruction and scene registration. The successful candidate will design robust algorithms for dynamic, cluttered surgical environments, enhancing calibration reliability, perception, and interaction between optical, depth, and inertial sensing modalities. Research domains include computer vision, computer graphics, and virtual/augmented/mixed reality. The role involves designing and implementing real-time multi-camera calibration and tracking algorithms using feature-based, fiducial, and self-supervised approaches; developing multi-sensor fusion pipelines integrating RGB, depth, and IMU data via Kalman/particle filters, SLAM, or factor-graph optimization; and building and training deep neural architectures (CNNs, transformers, NeRFs, diffusion or implicit 3D representations) for 3D reconstruction and surface registration. The candidate will also implement and test AI-driven calibration correction under occlusion, motion blur, and illumination changes, conduct quantitative evaluations on synthetic (Blender, Unreal Engine) and real datasets, and deploy algorithms on GPU/embedded platforms for integration with robotic testbeds at THINK Surgical. Collaboration with interdisciplinary teams and co-authorship of publications in top-tier venues such as CVPR, ICCV, ICRA, or MICCAI are expected. Applicants must have a strong background in computer vision, deep learning, and 3D geometry, with proficiency in Python and C++, and experience with relevant libraries and frameworks. The position offers access to advanced GPU clusters, motion-capture and XR facilities, and custom imaging testbeds at the Immersive and Creative Technologies (ICT) Lab. Supervision is provided by Professor Charalambos Poullis, an internationally recognized expert in computer vision and graphics. The PhD fellowship provides 23,000 CAD per year for 3 years, with additional support for technical training, conference travel, and interdisciplinary collaboration. Applications are accepted year-round. To apply, send a single PDF with required documents to volt-age.recruitment@concordia.ca. For questions, contact Alisa Makusheva at alisa.makusheva@concordia.ca.

Funding

Funded PhD Project (Students Worldwide)

How to apply

Send a single PDF containing a letter of intent, academic CV, transcripts, names and contact information of 3 referees, and publications (if any) to volt-age.recruitment@concordia.ca. Use the subject line 'IASO_Your name_PhD' and name the PDF file accordingly. Applications are considered on a rolling basis. For questions, contact Alisa Makusheva at alisa.makusheva@concordia.ca.

Requirements

Applicants must hold a Bachelor's, MSc, or PhD in Computer Science, Electrical or Software Engineering, or a related discipline. Proven experience in computer vision, deep learning, and 3D geometry (including camera models, epipolar geometry, and bundle adjustment) is required. Strong programming proficiency in Python and C++ is essential, with practical experience using PyTorch or TensorFlow for vision models. Experience with OpenCV, Open3D, PCL, ROS, or NVIDIA Isaac SDK is expected. Familiarity with structure-from-motion (SfM), visual SLAM, or multi-view stereo pipelines is important. Background in graphics or rendering engines (such as Unreal, Blender, or Unity) for synthetic data generation, as well as GPU acceleration and CUDA development, are considered assets. Excellent analytical, experimental design, and scientific writing skills are required.

Ask ApplyKite AI

Start chatting
Can you summarize this position?
What qualifications are required for this position?
How should I prepare my application?

Professors