Are you interested in revolutionizing the way people around the world enjoy live sports video? Come and join us and be part of the Prime Video Playback team. As a video scientist, you will:
· Drive novel live encoding optimization to ensure the best live sports streaming experience delivered to millions of global customers.
· Utilize the state-of-the-art computer vision and machine learning techniques to achieve content adaptive live sports encoding to maximize quality per bits at Amazon scale.
· Innovate in video quality measurement, video content analysis, and video compression technologies to lead the video industry/community.
A day in the life
As a video scientist in the Prime Video Playback, you will:
· Research and prototype innovative ideas in live sports content analysis, quality measurement, and content-adaptive live video encoding.
· Drive technical approach and innovation via proof-of-concept prototyping, paper/report writing, technical presentations and patent filing
· Collaborate with and influence product and engineering teams for technology productization and deployment
About the hiring group
The Live Encoding Optimization team's charter is to drive the live streaming video quality improvement at reduced bit costs and low latency, ensuring the best Prime Video customer experience across live sports events and live linear channels. Our innovative technical programs drive benefits at multiple levels: (1) Ensure the best live streaming video quality and Quality-of-Service (QoS) metrics for live events and live linear channel customers, (2) Reduce the live encoding (compute and bit) costs and the associated delivery cost, and (3) Elevate the industry-wide recognition of our innovations in content-driven encoding optimization and video quality measurement.
As a video scientist in the Prime Video Playback, this person shall:
· Get familiar with the latest development and advances in video processing, video compression, and computer vision and machine learning to video understanding and analysis
· Build research prototypes in live sports video content analysis, objective and subjective video quality measurement, and content-adaptive live video encoding.
· Document and present technical proposals and implementations to both internal and external stakeholders and partners.
· Work closely with engineering and product team to prioritize technology prototyping, productization and deployment
Amazon is committed to a diverse and inclusive workplace. Amazon is an equal opportunity employer and does not discriminate on the basis of race, national origin, gender, gender identity, sexual orientation, protected veteran status, disability, age, or other legally protected status. For individuals with disabilities who would like to request an accommodation, please visit https://www.amazon.jobs/en/disability/us.
· PhD or equivalent Master's degree plus 5+ years of research experience in a quantitative field
· 3+ years experience investigating the feasibility of applying scientific principals and concepts to business problems and products
· Master or PhD in Computer Science, Electrical Engineering or related fields with specialty in multimedia areas
· Expertise in video and/or image processing, computer vision and/or machine learning (CV/ML), video quality assessment, and video compression algorithms and systems.
· ~10 years of experience with problem solving in the video processing/CV/ML area
· Knowledge of algorithm complexity, real-time system implementation considerations, and the ability to design, implement, integrate, and test algorithms in both standalone or reference code bases.
· Good programming skills in Python, C/C++ or Java.
· Proven track record of publications, patents, and contributions in leading conferences/journals, streaming video industry or video compression standards
· Visibility in the industry through presentations/invited-talks
· Proven written and spoken communication skills
· Knowledge of competitive technologies and the trade-offs across complexity, quality, and compression on the encoding and decoding ends.
· Working knowledge of one or more deep-learning frameworks (Pytorch, Tensorflow, etc.) and Python coding skills
· Working Knowledge of objective and subjective video quality assessment methods and practices
· Working Knowledge of live encoding system and hands-on experience with bitrate, quality and latency tradeoff
· Knowledge of video streaming systems and related protocols