The main tasks you are expected to perform include, but are not limited to: Explore and experiment with emerging technologies to continuously improve our AI-driven content reconstruction, creation, and edition processes. Review the state of the art computer vision research papers and develop prototype solutions. Develop cutting-edge software and algorithms for computer vision, image processing, and deep learning models. Have technical responsibility for one or more significant sections of the assigned project. Translate complex functional and technical requirements into detailed design. Skills and Qualifications
Essential skills are: Currently studying for a PhD in Mathematics, Computer Science, or a related discipline (or just completing). Computer vision, machine/deep learning, or related fields. Expertise in image-based 3D reconstruction: Photogrammetry, Neural Radiance Fields (NERF), or Gaussian Splatting techniques. Strong programming skills in Deep Learning libraries like PyTorch and/or TensorFlow. Programming proficiency in one or more programming languages and APIs like C++/Java/Python. Excellent communication, teamwork, and a results-oriented attitude. Proficiency in problem-solving and debugging. Desirable skills include: Experience in Generative AI, including hands-on implementation of state-of-the-art models. Computational photography, image inpainting, and 3-D vision. Model optimization and knowledge distillation. Experience in computer graphics and rendering: design and development of software such as OpenGL, OpenGL ES, Vulkan, or DirectX. Experience in Android application development. Contract type: 6-month internship Start date: immediate start (as soon as possible) Location: Staines-upon-Thames, Surrey, UK Hybrid Policy: 3 days onsite and 2 days working from home weekly
#J-18808-Ljbffr