Applied Scientist - Multimodal Generative Modeling & IP Safeguards

Job description

Generative AI is redefining creativity. Ensuring that these systems are safe, controllable, and respectful of intellectual property is one of the most important open research challenges in the field. The Adobe Firefly Applied Science & Machine Learning team is building next-generation multimodal guardrail systems for building safe and compliant image, video, and audio generative models powering Firefly.com. Our goal extends beyond reactive blocking ; we are developing model-level guidance mechanisms that proactively steer generation away from IP-violating concepts while preserving creative intent and usability. We are seeking a P 4 0 Applied Scientist with strong multimodal depth and research instincts to help define and dev e lop the frontier of IP-aware generative modeling. This role sits at the intersection of generative model alignment, multimodal reasoning, and large-scale inference systems. Research Areas You Will Drive: Inference-Time Alignment & Optimization: Research and implement inference-time control techniques (guided decoding, constrained sampling, classifier guidance, reward-based steering). Optimize large multimodal systems for low-latency, production-scale deployme...