This job is with Amazon, an inclusive employer and a member of myGwork the largest global platform for the LGBTQ+ business community. Please do not contact the recruiter directly.
Description
This position involves developing advanced ML/DL models that continually improve Prime Video's Content Adaptive Encoding (CAE) practices for Video-on-demand (VoD) streaming use-case. You will work closely with subject matter experts (Research Scientists) with depth in the video encoding/quality/processing areas to maximize the video quality that Prime Video customers experience under a given network condition.
Your work would directly influence the customer experience and will also help drive efficiency related business goals. The work would involve working with creation and cleaning of ground-truth datasets driving the model, feature engineering, development of classification or regression ML/DL models with high accuracy, optimization and deployment of such models in production workflow, and defining/measuring suitable at-scale success criteria.
Key job responsibilities
You would develop ML/DL based classification/regression models based on content properties across the processing chain involved in encoding, including changes within modern encoders to reduce run-time or to improve the level of adaptation to content properties. You would work across multiple codecs including next-gen codecs, standard and High Dynamic range content. Aspects of work can involve scene understanding at a semantic level using latest techniques. You would develop innovative solutions that achieve the best balance between speed vs performance. You would collaborate with research scientists with domain depth in video encoding/compression. You would conduct subjective ratings tests to generate ground truth data for your models, when required. You would develop novel approaches to perform fast searches in high dimensional parameter space. You would contribute to development of new video quality models that correlate highly with subjective ratings. You would define and refine team processes around ML/DL model development, deployment, and guardrail definition.
A day in the life
You will work with L5-L8 Research Scientists within the team who will bring the specific problem definition required to set and meet annual goals, 3Y/5Y roadmap items. You will work with University partners who help PV explore new problem areas. You will interface with SDEs to convert the output of the research team into production workflows. You will develop new AI workflows that are more efficient from a compute perspective. You will write disclosures capturing innovative ideas in realizing low complexity, highly performant ML/DL methods and will then publish papers in internal and external conferences.
About The Team
Our mission is to build and operate the most innovative video streaming technology stack that provides the best customer-centric streaming experience for VOD and Live globally and supports all business use cases (subscription, transactional, ad-supported). We invent and implement technologies that deliver a flawless, engaging streaming experience for our customers, using the fewest bits possible. We commit to our values of respect and integrity by creating a work environment that is supportive, diverse, inspiring, and inclusive.
Basic Qualifications
- 3+ years of building machine learning models for business application experience
- PhD, or Master's degree and 6+ years of applied research experience
- Experience programming in Java, C++, Python or related language
- Experience with neural deep learning methods and machine learning
- Experience in patents or publications at top-tier peer-reviewed conferences or journals
Preferred Qualifications
- Experience with modeling tools such as R, scikit-learn, Spark MLLib, MxNet, Tensorflow, numpy, scipy etc.
- Experience with conducting research in a corporate setting
- Experience developing and implementing deep learning algorithms, particularly with respect to computer vision algorithms
