— Master’s degree in Computer Science, Engineering, or a related field
— 4+ years of professional experience working in Computer Vision, Machine Learning, Data, or a related field.
— Proficient in at least one deep-learning framework (Tensorflow, PyTorch, etc.)
— Proficient in ML model optimization techniques
— Strong verbal and written communication skills
— Strong background in data and analytics
— Experience with distributed computation frameworks (Spark, Hive, Dask, Metaflow, etc.), job orchestration (Airflow, Luigi, etc.), and databases (MySQL, PostgreSQL, etc.)
— Experience working with video—transport streams, video capture, video processing, transcoding, frame analysis, ffmpeg
— Proficient knowledge of Linux and solid command of version control systems
— Research, survey, and prototype different model optimization techniques (quantization,compression, etc.) with or without systems-hardware co-design
— Develop proofs-of-concept of customized optimizations and demonstrate the benefit ofyour optimizations
— Incorporate model optimization into existing model training and post-training phases ofthe Core AI workflow
— Work closely with the TV embedded team on the implementations of the optimizedmodels
Our partner is on a mission to fundamentally change television viewing for everyone. They are doing this by leveraging our data to enable advertisers to engage and measure TV viewers across all their devices. They have an amazing story with a unique perspective formed by innovative technology.
Their team is in charge of building models for the next generation of AI-powered TV products. They are responsible for the end-to-end development of our models, including
— dataset collection using geographically-distributed television labs;
— model training in the cloud using serverless GPU clusters;
— model optimization for constrained computation on the edge;
— model testing using both virtual and real televisions; and
— development of the AI platform that makes the above possible.
As a member of their team you will be working at the intersection of engineering, science, and entertainment. As an ML Optimization Engineer, you will take the models we run in the cloud or other large reference models and optimize them to run on the constrained resources of an edge device, such as a TV.