Responsibilities
- Research video analysis algorithms for region-of-interest detection, content understanding, feature extraction, and perceptual quality assessment.
- Design and implement objective and learning-based image/video quality evaluation methods.
- Build datasets, benchmarks, and evaluation pipelines for multimedia quality and content analysis.
- Develop end-to-end video quality optimization solutions involving analysis, enhancement, processing, and encoding.
- Apply algorithms to VOD and live-streaming use cases, including quality monitoring, data analysis, evaluation, and performance validation.
- Prototype, train, and optimize machine learning and deep learning models for multimedia tasks.
- Collaborate with infrastructure, platform, and engineering teams to integrate research prototypes into production workflows.
- Conduct offline experiments, online validation, and A/B testing analysis.
- Document research findings and communicate technical insights to research and engineering stakeholders.
Requirements
- Currently pursuing a PhD in Computer Science, Electrical Engineering, Mathematics, Statistics, or a related technical field.
- Strong programming, debugging, and optimization skills in one or more general-purpose languages, including C/C++ and/or Python.
- Understanding of image/video analysis or image/video quality assessment methods.
- Familiarity with objective quality metrics such as VMAF, PSNR, and SSIM.
- Hands-on machine learning or deep learning experience and familiarity with PyTorch or TensorFlow.
- Ability to conduct experiments independently, analyze results rigorously, and iterate based on data.
- Strong written and verbal communication skills for collaborative research and engineering work.
- Preferred qualifications include experience with Transformer architectures, multimodal large models, vision-language/video-language modeling, video enhancement, codecs, perceptual optimization, learned compression, multimedia deployment, large-scale evaluation, embedded systems, ARM or RISC-V processors, or RTOS environments.
Benefits
- PhD internship with opportunities to contribute to products, research, future plans, and emerging technologies.
- Hands-on learning, community-building, professional development events, and collaboration with industry experts.
- Applications are reviewed on a rolling basis; applicants should state their availability, including start and end dates, on their resume.
Categories
About ByteDance
ByteDance is a global incubator of platforms at the cutting edge of commerce, content, entertainment and enterprise services - over 2.5bn people interact with ByteDance products including TikTok. Creation is the core of ByteDance's purpose. Our products are built to help imaginations thrive. This is doubly true of the teams that make our innovations possible. Together, we inspire creativity and enrich life - a mission we aim towards achieving every day. At ByteDance, we create together and grow together. That's how we drive impact - for ourselves, our company, and the users we serve. We are committed to building a safe, healthy and positive online environment for all our users. We have over 110,000 employees based in more than 30 countries globally. Join us.