Overview In this role, you will advance computer vision and ML methods to build a scalable video content risk inspection platform. You will collaborate with cross-disciplinary researchers to define the scope, prototype innovative solutions, and compare approaches to deliver high-precision, low-latency models for customer-facing applications. You will engage with software teams to deploy vision-based systems at scale and solve challenging problems that have not been solved before. This opportunity offers strong learning growth and meaningful impact for millions of users. ResponsibilitiesDevelop and apply CV/ML methods to text metadata, video, audio, and images for content risk assessmentPrototype and test solutions; compare approaches to optimize accuracy and latencyCollaborate with researchers and software teams to define product scope and build robust vision-based systemsOperate in ambiguous environments, solving scale-out problems and driving performance improvementsContribute to a platform processing terabytes of video content and deliver customer-facing outcomes Key requirementsPhD in Computer ScienceDepth and breadth in state-of-the-art computer vision and machine learning technologies5+ years of hands-on experience in predictive modelling and analysisStrong algorithm development experienceProgramming skills in Java, C++, and Python or similar scripting languagesDepth and breadth in CV/ML technologiesability to work in ambiguitycollaborative mindsetproblem-solving orientationstate-of-the-art computer vision technologiesmachine learning and deep learningpredictive modelling and analysis
Not specified in the original listing.
Not specified in the original listing.
