AI Researcher Audio And Multimodal AI

The Institute

Technology Innovation Institute (TII) is a publicly funded research institute, based in Abu Dhabi, United Arab Emirates. It is home to a diverse community of leading scientists, engineers, mathematicians, and researchers from across the globe, transforming problems and roadblocks into pioneering research and technology prototypes that help move society ahead.

AI and Digital Science Research Centre

The Artificial Intelligence and Digital Science Research Centre (AIDRC) is the machine learning powerhouse of TII. We work closely with other research centers to harness the full potential of AI across multiple domains — from healthcare and cybersecurity to government and advanced technology systems.

We incorporate core elements of intelligence (perception, sensing, planning, and language) in the ideation, design, and prototyping of next-generation systems with human-like intelligence. We build advanced AI computing and scalable AI-based software stacks and hardware systems to deliver significant enhancements in systems infrastructure.

Our AI researchers, scientists, and engineers collaborate to ensure innovative outcomes, from AI theory to AI technologies towards better intelligence.

Job description

We are seeking a talented and motivated AI Researcher — whether early-career or experienced — to join our team and contribute to cutting-edge research in multimodal generative AI, with a primary focus on audio, spanning speech, music, and sound. The successful candidate will bring strong technical foundations and scientific curiosity, with the opportunity to grow into research leadership, shape our audio AI program, build strategic partnerships, and produce impactful contributions that advance both the field and the capabilities of our center.

Tasks related to the job

Research Leadership

• Contribute to and progressively lead research programs in multimodal foundation models, with a particular emphasis on Speech/Audio Large Language Models (LLMs) and generative audio systems
• Participate in defining research direction — identifying high-impact opportunities and aligning scientific priorities with the center's strategic goals.
• Support and, over time, mentor junior researchers and engineers, contributing to a culture of scientific excellence and continuous learning.
• Engage actively in decisions regarding research roadmaps, model development priorities, and team initiatives.

Scientific & Technical Excellence

• Design, implement, and rigorously evaluate novel model architectures and training algorithms for audio and multimodal generative systems.
• Participate in the full research lifecycle: dataset curation and selection, model training, fine-tuning, scaling, and systematic performance evaluation.
• Contribute to large-scale data processing and experiment management across distributed training environments.
• Drive open-source releases and publish research findings in top-tier venues, contributing to the external profile of the research center.

Collaboration & External Engagement

• Collaborate with internal research centers, industry partners, academic institutions, and end-user communities to advance shared research goals.
• Present research outcomes through publications, technical reports, demonstrations, and conference presentations at leading venues.
• Contribute to proposals for new research programs and strategic initiatives in collaboration with senior researchers and leadership.

Responsible AI & Governance

• Ensure adherence to ethical standards, responsible AI practices, and AI safety guidelines.
• Contribute to establishing best practices, shared infrastructure, and reusable research components across teams.

Required qualifications and skills

• PhD in Computer Science, Artificial Intelligence, Electrical Engineering, or a related field (strongly preferred), or a Master's degree with demonstrated research experience and output.
• Expertise or strong research interest in audio AI — including one or more of: speech/audio generation, text-to-speech (TTS), text-to-music/sound generation, speech recognition, audio representation learning, audio language models, video-to-audio generation, audio-visual learning, or lip sync.
• Evidence of research output — including publications, preprints, thesis work, or open-source contributions — demonstrating scientific rigor and originality.
• Solid understanding of modern AI architectures, training paradigms, and evaluation methodologies.
• Hands-on experience (including through research projects or thesis work) in at least one of: audio dataset curation, model training, or audio generation evaluation.
• Proficiency in Python and experience with PyTorch or TensorFlow.
• Good written and verbal communication skills, with the ability to present research ideas clearly and concisely.

Nice to have

• Patents in AI, audio, speech, music, or multimodal learning domains.
• Publications in top-tier speech & audio venues: ICASSP, Interspeech, ASRU, SLT, WASPAA, DCASE, or EUSIPCO.
• Publications in music and MIR venues: ISMIR, SMC, NIME, DAFx, ICMC, or the AES Conference.
• Publications in leading journals: IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP), Transactions of the ISMIR (TISMIR), Journal of the Acoustical Society of America (JASA), IEEE Signal Processing Letters (SPL), or EURASIP Journal on Audio, Speech and Music Processing.
• Publications in top general AI/ML conferences: NeurIPS, ICML, ICLR, AAAI, ACL, EMNLP, or ACM Multimedia.
• Experience in ML or audio competitions such as Kaggle, DCASE Challenge, or similar domain-specific benchmarks.