Research Scientist, Reward Modeling & Post-Training Equity

Google LLC; Zürich; On-site; CHF 150,000 - 210,000; Full time

Job summary

Google DeepMind in Zürich is seeking a Research Scientist to advance the post-training strategy for our Gemini User Signals team. You will convert complex user interactions into training signals to improve model behavior and alignment.

You will lead research into reward modeling, preference optimization, and data-centric strategies, developing scalable recipes across modalities and model families. We value publications, strong Python and DL framework skills, and collaboration with

Qualifications

• PhD in ML/NLP or equivalent experience.
• Strong Python and deep learning framework skills.
• Research in post-training, RL, or reward modeling.
• First-author publications in ML/NLP venues.

Responsibilities

• Harvest and utilize high-quality user signals to improve Gemini models.
• Develop reward models and critique models for RLHF and alignment.
• Create horizontal post-training recipes across models and modalities.
• Investigate data weighting and selection to maximize signal impact.
• Establish evaluation frameworks linking offline metrics to user satisfaction.

Skills

Python

RL research

Reward modeling

Preference learning

Deep learning

Education

PhD in ML/NLP

Tools

PyTorch

JAX

Job description

Google DeepMind in Zürich is seeking a Research Scientist to advance the post-training strategy for our Gemini User Signals team. You will convert complex user interactions into training signals to improve model behavior and alignment.

You will lead research into reward modeling, preference optimization, and data-centric strategies, developing scalable recipes across modalities and model families. We value publications, strong Python and DL framework skills, and collaboration with