Lead the ShortForm Pod: Define the technical roadmap for automated clip generation and video insight, managing a high-performing pod of ML engineers.
Architect Multi-Modal Models: Design and deploy models that synthesize signals across video (pixels), audio (speech/music), and text (transcripts/scripts) to understand content context.
Own Video Intelligence: Develop and scale robust computer vision and audio classifiers for nudity, profanity, and sensitive content detection.
Advance Narrative Understanding: Build models that can identify "hooks," "climax points," and "narrative summaries" to automate the creation of trailers and highlights.
Spoiler & Context Detection: Create intelligence layers that identify plot-critical "spoilers" to ensure ShortForm assets don't ruin the viewing experience for new users.
Scalable Content Pipelines: Partner with Content Engineering to integrate these models into petabyte-scale video processing workflows.

6-8+ years of experience in machine learning, with a heavy focus on Computer Vision (CV) and Multi-Modal architectures.
Mastery of PyTorch or TensorFlow, specifically for video-based tasks (e.g., Video Transformers, 3D CNNs).
Proven experience building safety/moderation models (Nudity, Profanity, Hate Speech) or content-tagging systems.
Experience leading senior technical teams and translating complex "creative" goals into engineering requirements.
Knowledge of video processing frameworks (FFmpeg) and handling various codecs/resolutions at scale.
Experience with Generative AI for Video (automated editing or style transfer).
Background in NLP/Speech for sync-ing transcripts with video frames.
Knowledge of Narrative Theory or experience in the media/entertainment industry.
Experience deploying large-scale models in Cloud Environments (AWS/GCP/Azure) with high GPU utilization efficiency.

Principal Machine Learning Engineer, Content Engineering

Key skills