Research Scientist - Multimodal Agent, Consumer Devices

Openai; Deutschland; Vor Ort; EUR 158.032 - 210.710; Vollzeit

Benefits dieser Stelle

Relocation assistance

Hybrid work model (4 days in office)

Zusammenfassung

OpenAI is seeking a Research Engineer/Scientist to join the Future of Computing Research team in San Francisco, CA. The role focuses on RLHF and post-training for personalized, multimodal AI systems, building learning and evaluation foundations for context-aware models.

The ideal candidate will push beyond one-turn assistant behavior toward systems that learn from feedback, with long-horizon evaluation and policy improvement, in a highly product-grounded setting.

Qualifikationen

• Experience building RLHF systems and post-training pipelines.
• Familiarity with reward modeling and preference learning.
• Experience with long-horizon evaluation and model-guided policy improvement.
• Ability to design datasets, rubrics, and evaluation frameworks.
• Strong collaboration with safety research teams to ensure responsible AI behavior.

Aufgaben

• Develop RLHF and post-training methods for multimodal models.
• Build reward models and preference-learning pipelines for adaptive, personalized model behavior.
• Design datasets, rubrics, and evaluation frameworks that capture user preferences and long-term value.
• Run experiments on policy improvement using explicit/implicit feedback and model-based grading.
• Tackle long-horizon evaluation problems where outcomes improve over time.
• Collaborate closely with safety researchers to ensure aligned and bounded adaptation.

Jobbeschreibung

About the Team

The Future of Computing Research team is an applied research team within the Consumer Devices group focused on developing new methods, models, and evaluation frameworks that support our vision for the future of computing. We work at the frontier of multimodal AI, helping turn emerging model capabilities into product experiences that are useful, delightful, and worthy of long-term trust.

Our work explores a new class of AI systems that can learn over time, adapt to individuals, and support people in the flow of daily life. This includes long-term memory, user modeling, and personalization systems that are aligned not just with immediate satisfaction, but with a person’s broader goals, values, and well-being.

We work closely across research, engineering, design, product, and safety to define what it means to build AI systems that know you over time, act at the right moment, and help in ways that are context-aware, respectful, and demonstrably beneficial.

About the Role

We are looking for a Research Engineer / Scientist to join the Future of Computing Research team to work on RLHF and post-training for personalized, multimodal AI systems.

This role will focus on building the learning and evaluation foundations that help models become more context-aware, adaptive, and useful over time. You will work on problems such as reward modeling, preference learning, long-horizon evaluation, and policy improvement for systems that must make high-quality behavioral decisions in realistic user settings. The work is deeply product-grounded: success is not just higher benchmark performance, but better model behavior in real-world use.

The ideal candidate is excited about pushing beyond one-turn assistant behavior toward systems that improve through feedback, learn from richer signals, and are trained against meaningful notions of user value. Internally, that maps closely to the need for careful reward design, feedback loops, and evaluation frameworks that test whether interventions are actually beneficial over longer horizons.

This role is based in San Francisco, CA. We use a hybrid work model of four days in the office per week and offer relocation assistance to new employees.

In this role, you will:

• Develop RLHF and post-training methods for multimodal models.
• Build reward models and preference-learning pipelines for adaptive, personalized model behavior.
• 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 behavior improves outcomes over time.
• Collaborate closely with safety researchers to ensure that adaptation and personalization remain aligned, interpretable, and bounded by clear constraints.
• Pr