Principal Video Specialist

Job ID: 1539669 | ADCI - Karnataka

DESCRIPTION

DESCRIPTION
Amazon Go is a new kind of store with no lines and no checkout—you just grab and go! Customers simply use the Amazon Go app to enter the store, take what they want from our selection of fresh, delicious meals and grocery essentials, and Just Walk Out! Amazon Go is a rapidly accelerating new business seeking to reinvent physical retail. The technologies we have built has enabled us to offer this new exciting business to customers around the world. However, we will need to overcome unique challenges in order to scale as quickly as we can, and as operationally efficient as possible. This will require us to be creative in our approach.

One of our major challenges is the amount and quality of video data each store needs to compress and analyze, including 4k HEVC, high dynamic range video, and cloud transcoding and storage. This puts a huge strain on end-to-end systems that handle video, including network bandwidth, cloud servers (CPU and GPU), and even browsers, from all over the world. Doing this efficiently and optimally, for our specific use cases, is our constant challenge. We are seeking a Principal Scientist, with deep expertise in video compression and processing. Your responsibilities will include everything from developing and prototyping innovative video compression, representation and retrieval algorithms to implementing, testing, and supporting full solutions in a production environment.

The Role:
As a hands-on leader of this team, you’ll be responsible for defining key research questions, identifying relevant data for experiments and algorithm evaluation, adopting and/or developing innovative video compression, representation and retrieval algorithms, conducting rigorous experiments, publishing results and working with the engineering team to deploy these solutions. As a strategic leader, you will identify investment opportunities, develop long term strategies, and propose, prioritize and deliver on goals. You will illuminate and clarify and relentlessly focus on Invent and Simplify, in order to build scalable science and engineering solutions. You will serve as a key scientific resource in full-cycle development (conception, design, implementation, testing to documentation, delivery, and maintenance).

What you’ll do:
1. Work with modern video applications that often involves capture device (camera HW), device SW, network transmission, receiver, and display.
2. Have broad understanding of camera design, Image Signal Processing (ISP), video compression, metrics of video quality and accuracy, and drive for global optimization related to various use-cases of video.
3. Develop methodologies to improve video accuracy while optimizing for limited hardware and software resources for all Amazon Go’s use cases.

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.

BASIC QUALIFICATIONS

1. PhD (preferred) or Masters in EE or CS. (video/compression emphasis)
2. 10+ years of work experience with compression algorithms, video systems, and video quality measurement related jobs.
3. Experience in video quality assessment and video analysis.
Experience with full stack system development.

PREFERRED QUALIFICATIONS

1. 10+ years experience
2. Proven track record of contributions to video compression standards
3. Several granted patents and publications in the space of video coding and deep learning
4. Visibility in the industry through presentations/invited-talks
5. Proven written and spoken communication skills
6. Knowledge of video streaming systems and related protocols
Knowledge of competitive technologies and the trade-offs across complexity, quality, and compression on the encoding and decoding ends.