Design and execute white-box attacks against advanced AI models, checkpoints, post-training systems, reward functions, data pipelines and evaluation environments.
Locations (2)
Redmond, Washington, United States
United States
Compensation
Research Sciences IC5 - The typical base pay range for this role across the U.S. is USD $142,800 - $274,800 per year. There is a different range applicable to specific work locations, within the San Francisco Bay area and New York City metropolitan area, and the base pay range for this role in those locations is USD $188,000 - $304,200 per year.
Responsibilities
Design and execute white-box attacks against advanced AI models, checkpoints, post-training systems, reward functions, data pipelines and evaluation environments.
Investigate adversarial behavior including jailbreaks, harmful permissiveness, reward hacking, deceptive behavior, capability elicitation, privacy leakage, data poisoning and model supply-chain compromise.
Build high-fidelity experiments and automated attack suites that reproduce realistic threats and run continuously against new checkpoints and system configurations.
Lead the design, development, and delivery of data products for trust & safety in AI, including RL environments, safety traps, and evaluation metrics for frontier labs.
Compensation
The expected salary range for this position is $180,000 – $220,000 USD per year, based on experience, skills, and qualifications.
Conduct research on generative recommendation systems, develop models, and collaborate with researchers and engineers to advance personalized retrieval and ranking.
Responsibilities
Conduct research on generative recommendation, including autoregressive transformers, diffusion models, and flow matching for personalized retrieval and ranking
Explore multimodal modeling approaches that combine images, video, text, and user interaction histories to learn content representations and user preferences
Develop reinforcement learning, reward modeling, and preference optimization methods to improve recommendation quality and long-term user satisfaction
Design, implement, and evaluate novel model architectures and training algorithms through rigorous experimentation
Collaborate closely with researchers and engineers to translate research ideas into scalable recommendation methods
Requirements
Ph.D. in Computer Science, Electrical Engineering, or a related field
Technical Product Manager, Trust & SafetyInnodata Inc. · Remote, US
Research Scientist Intern, Generative Recommendation (PhD)Meta · Singapore, Singapore