Staff Researcher, Multimodal

Via Licensing Corporation; Bengaluru; On-site; INR 3,000,000 - 5,000,000; Full time

Job summary

Via Licensing Corporation is seeking a Staff AI Researcher to join the Multimodal Experiences Lab, focusing on developing multimodal AI systems that enhance audio-visual experiences. This role requires a PhD or equivalent experience with a minimum of 6 years in AI, and deep expertise in multimodal and generative AI.

The successful candidate will lead research initiatives, mentor junior researchers, and collaborate with teams at Dolby to translate innovations into production. This position is based in Bengaluru, Karnataka, India.

Qualifications

• Minimum 6+ years of experience in AI research and/or industry.
• Proven experience leading research projects with cross-team impact.
• Experience translating research into real-world systems or products.

Responsibilities

• Help define and drive research directions in multimodal AI for immersive audio-visual experiences.
• Design and develop novel AI models for content creation, enhancement, and rendering.
• Collaborate with engineering and business teams to bring innovations into production.

Skills

Multimodal AI

Generative AI

Computer Vision

Audio/Audiovisual Analysis

Python

C/C++

Education

PhD in a relevant field or equivalent research experience

Tools

Deep Learning

Prototyping

Job description

We are seeking a Staff AI Researcher to join the Multimodal Experiences Lab within Dolby’s Advanced Technology Group. Our team invents next-generation technologies that power immersive audio‑visual experiences, combining machine learning with Dolby’s leadership in perceptual signal processing. In this role, you will help drive the development of multimodal AI systems that transform how content is created, delivered, and experienced by driving research from early exploration through deployment in Dolby technologies.

Key Responsibilities

• Help define and drive research directions in multimodal AI for immersive audio-visual experiences.
• Design and develop novel AI models for content creation, enhancement, and rendering.
• Integrate deep learning with perceptually grounded signal processing and quality metrics.
• Drive end-to-end research initiatives, from ideation through prototyping and technology transfer.
• Collaborate with engineering and business teams to bring innovations into production.
• Influence Dolby’s long-term technology strategy and roadmap in multimodal AI.
• Mentor and develop junior researchers, fostering technical growth and research excellence.
• Represent Dolby externally through publications, patents, and engagement with the research community.

Required Skills

• PhD in a relevant field or equivalent research experience with significant demonstrated impact.
• Minimum 6+ years of experience in AI research and/or industry.
• Deep expertise in one or more areas: multimodal AI, generative AI, computer vision, audio/audiovisual analysis.
• Proven track record of innovation, including first-author publications and/or patents in top-tier venues (e.g., CVPR, NeurIPS, ICML, ICLR, ICCV).
• Proven experience leading research projects or initiatives with cross-team impact.
• Experience translating research into real-world systems or products.
• Proficiency in Python and/or C/C++ with hands‑on prototyping experience.
• Strong communication and collaboration skills across research, engineering, and product teams.

Desired Skills

• Experience with perceptual quality metrics for audio and/or video.
• Familiarity with real-time or production‑scale media systems.
• Experience with GPU/CPU architectures, embedded systems, or ML deployment on SoCs.