Research Assistant - Computer Vision and Robotics (Fixed Term)
Fixed-term: Funds are available for a period of 6 months.
We are seeking a Research Assistant (RA) to join the Prorok Lab at the University of Cambridge's Department of Computer Science and Technology for 6 months in the first instance. This position focuses on the engineering development and deployment of 3D scene understanding models for robotic applications.
The successful candidate will work with our team to transition existing research prototypes to operational systems, laying the groundwork for a planned spin-off. The ideal candidate will be self-motivated, solutions-oriented, and passionate about implementing robust robotic systems. While based in an academic setting, this is primarily an engineering role focused on practical implementation and deployment, with the opportunity to transition to a startup environment. This position also represents an opportunity to join an emerging company at its foundation.
The Prorok Lab maintains state-of-the-art aerial and ground robotic platforms and specializes in practical robotics deployment and multi-robot coordination strategies. Our recent achievements in cooperative perception and graph neural networks (GNNs) showcase our technical direction.
Qualifications:
- Bachelor's or Master's degree in Computer Science or related field, or equivalent industry experience
- Strong proficiency in Python and PyTorch
- Solid foundation in classical computer vision and 3D data processing
- Experience with deep neural networks and vision transformers
- Hands-on experience with robotic systems
- Experience in C++ or Rust is highly desirable
Responsibilities:
- Process and prepare real-world and simulation datasets for model training
- Develop and train deep neural networks for 3D scene reconstruction in robotic applications
- Optimize architectures for edge deployment (Nvidia Jetson, Raspberry Pi with Hailo accelerator)
- Implement TensorRT optimizations and model quantization
- Conduct performance benchmarking against reference sensors
- Develop and document software libraries for embedded deployment
Join us in bridging the gap between research innovations and real-world robotic applications, with the potential to shape the future of multi-robot systems.
Click the 'Apply' button below to register an account with our recruitment system (if you have not already) and apply online.
Applicants should contact Prof Amanda Prorok for further information. http://www.proroklab.org
Please quote reference NR45112 on your application and in any correspondence about this vacancy.
The University actively supports equality, diversity and inclusion and encourages applications from all sections of society.
The University has a responsibility to ensure that all employees are eligible to live and work in the UK.