AI Multimedia Generation Product Evaluator

Job Title: AI Multimedia Generation Product Evaluator Location: California/Remote Duration : 3 Months Interview Mode : Video Job Description : The Multimedia Generation team focuses on fine tuning and productionizing media foundational models in the GenAI space. The team consists of AI applied scientists of five members, each responsible for different products like videos, image editing, and developing evaluation metrics. We are seeking a highly motivated and detail-oriented individual to join our team as an AI Multimedia Generation Product Evaluator. In this role, you will support the evaluation of various AI multimedia generation products for images and videos. You will work closely with model development teams to conduct offline evaluations, connect offline metrics with online user behavior, and ensure offline metrics are predictive of online user engagement. Responsibilities: • Set up Halo tasks and run model inference • Enqueue new queues to Halo • Audit annotations from vendors • Build necessary tooling for managing evaluation datasets • Collaborate with model development teams to conduct offline evaluations and automate pipelines • Facilitate, set up queues, manage image radio data, and audit results • Ensure consistency and accuracy in measurements, involving programming and auditing tasks Requirements: • 1-2 years of basic Python knowledge, particularly in working with image/video data and JSON • Experience in SQL and handling large data tables • Experience in the image and video domain • Ability to adapt to new code • General know-how • Flexibility in working hours Nice-to-Have Skills: • Experience as a GenAI user in the image and video domain • Basic shell script knowledge Degrees/Certifications - Bachelor s preferred, not required Apply tot his job