Senior Machine Learning Engineer, Content Understanding & Moderation

Written by the T&S Network from Unity's posting.

Machine learning work on the content side of Unity Ads, covering both the ad creatives shown and the games they run in. The team's charter spans turning creatives and games into signals for models, and detecting and acting on content that violates policy, regulation, or advertiser and publisher expectations, using one shared multimodal foundation for relevance and moderation.

What you'd do

• Build a shared multimodal content representation across video, images, playables, audio, and text for relevance and moderation
• Turn legal and contract requirements into measurable targets for ML models
• Set success criteria for contested labels that are sparse or noisy, then build tooling to track them
• Build labeling pipelines, content embeddings, game level features, and evaluation harnesses for other teams
• Partner with product, engineering, and science teams on content understanding and moderation objectives
• Review and remain accountable for production code, including code written with AI assistance

What it asks for

• Background in multimodal ML that combines vision and language models, with video especially relevant
• Hands-on time with ambiguous or disputed labels where what counts as a violation keeps changing
• Production experience tuning foundation models through fine-tuning, distillation, and speed and cost optimization
• Solid Python and experience running ML systems that serve live traffic
• Familiarity with DSA, child-directed treatment rules, and regional advertising standards (preferred)
• Systems thinking across performance, scalability, reliability, and cost in distributed systems (preferred)

Our best summary of the posting, and it can be wrong. The employer's posting is what counts: read it in full on Unitynorth_east before you apply. If we got something wrong, report this listing.