Multimodal AI Scientist for Personalization in Consumer Devices

OpenAI; San Francisco (CA); Hybrid; USD 380,000 - 445,000; Full time

Benefits offered by this job

Hybrid work model

Relocation assistance

Job summary

OpenAI is seeking a Research Scientist for the Multimodal Agent role in San Francisco to advance RLHF and post-training for personalized AI systems integrated into consumer devices. The position emphasizes learning foundations, reward modeling, and evaluation in real-world settings.

You will collaborate with safety researchers to ensure responsible adaptation, build training pipelines, and shape product-relevant behaviours with a focus on user value over time.

Qualifications

• Strong background in machine learning research with RLHF experience.
• Experience building reward models, preference learning, or post-training for large models.
• Ability to design clean experiments and meaningful evaluation metrics.

Responsibilities

• :Develop RLHF and post-training methods for multimodal models.
• Build reward models and preference-learning pipelines for adaptive, personalised model behaviour.
• Design datasets, rubrics, and evaluation frameworks that capture user preferences, contextual appropriateness, and long-term value in realistic tasks.
• Run experiments on policy improvement using explicit feedback, implicit signals, and model-based grading.
• Work on long-horizon evaluation problems, where model quality depends not just on a single response but on whether behaviour improves outcomes over time.
• Collaborate closely with safety researchers to ensure that adaptation and personalisation remain aligned, interpretable, and bounded by clear constraints.
• Prototype and iterate quickly on training recipes, reward formulations, data pipelines, and evaluation suites for product-relevant behaviours.
• Help define how OpenAI measures success for personalised AI systems including trust, appropriateness, and long-term user benefit.

Skills

RLHF

Reward modelling

Preference optimisation

Post-training

Multimodal models

Evaluation frameworks

Empirical ML

Job description

OpenAI is seeking a Research Scientist for the Multimodal Agent role in San Francisco to advance RLHF and post-training for personalized AI systems integrated into consumer devices. The position emphasizes learning foundations, reward modeling, and evaluation in real-world settings.

You will collaborate with safety researchers to ensure responsible adaptation, build training pipelines, and shape product-relevant behaviours with a focus on user value over time.