Our team at the Singapore University of Technology and Design (SUTD) is looking at generative AI models for music. You will be joining our Audio, Music, and AI (AMAAI) Lab supervised by Prof. Dorien Herremans. At our lab, we aim to advance the state-of-the-art in AI for music and audio. You will be working on advancing the Mustango text-to-music model.

Ideal skillset:

• Strong knowledge of deep neural networks in PyTorch
• Interest in machine learning for audio
• Experience in NLP and computer vision
• Experience in Music Information Retrieval, ideally AI music generation and or audio transcription
• Interest or experience in music generation systems or audio classification systems
• Savvy programmer in PyTorch
• Creative problem solver with good academic writing skills

An ideal candidate should have a strong background in machine learning, familiarity in NLP and audio computing, PhD in Computer Science and related areas, and willing to work with PhD students in the lab to leverage individual efforts into a combined system.

Job Summary: We are in search of a highly motivated and accomplished Senior Research Assistant or Research Associate to join our team and contribute to our ongoing research project "Towards Realistic Deep Learning for 3D Vision". The successful candidate will collaborate closely with our research team, working on the development of ground-breaking algorithms and methodologies for 3D deep learning from heterogeneous data sources such as language and 3D data. This role offers an exciting opportunity to engage in cutting-edge research and have a substantial influence on the field.

Responsibilities:

• Undertake research in the field of realistic 3D deep learning, with a primary focus on pioneering algorithms and methodologies with language-guided 3D scene understanding.
• Design and execute experiments to validate the proposed approaches.
• Analyze and interpret data sourced from heterogeneous inputs.
• Stay up-to-date with the latest advancements in language-guided 3D scene understanding and related fields, and integrate new findings into research projects.
• Prepare research papers for publication in prestigious conferences.

Qualifications:

• A Master degree in computer science, Electrical Engineering, or a related discipline, with a specialization on computer vision, image processing, or 3D reconstruction.
• A strong background in computer vision, machine learning, and 3D geometry.
• Proficiency in programming languages such as Python, C++, or MATLAB.
• Experience with relevant software libraries and frameworks, such as Pytorch, OpenCV, or PCL.
• A solid grasp of mathematical concepts related to 3D computer vision, including geometry, optimization, and statistical methods.
• Good problem-solving and analytical abilities.
• Strong communication skills