Research Scientist, User Signals from Agentic Logs, DeepMind

Google accountants are a savvy bunch who handle the core accounting responsibilities at Google. You know your accounting principles and the full accounting process end to end. You'll advise on financial reports required by governmental regulations, and review, analyze, and interpret financial and budgetary reports. Every day is a new challenge, and you're continually looking for ways to help our team become more efficient and effective. A team player at heart, you collaborate with our global team, advocate best practices and pitch in where needed. You move fast while keeping your attention to detail, and you tap into your problem-solving skills to support business objectives.

You'll lead an accounting process from end-to-end. Other responsibilities include reconciling balance sheets and P&L accounts, and providing supplementary financial information for internal and external reports.

In this role, you will operate at the intersection of accounting domain expertise and data engineering. You will combine an automation and AI-first builder mindset with accounting fluency to modernize financial reporting architectures, eliminate manual data manipulation, and build scalable system solutions. Working cross-functionally with operational accounting teams, central engineering and the Data and AI teams. You will lead the evolution of our financial data infrastructure to deliver actionable, driver-based insights that satisfy our reporting deliverables and partner needs. The name Google came from "googol," a mathematical term for the number 1 followed by 100 zeros. And nobody at Google loves big numbers like the Finance team when providing in depth analysis on all manner of strategic decisions across Google products. From developing forward-thinking analysis to generating management reports to scaling our automated financial processes, the Finance organization is an important partner and advisor to the business.Individual pay is determined by factors including job-related skills, experience, and relevant education or training.

US: $157000 - $227000 (USD) + 20% bonus target + equity + benefits

Learn more about benefits at Google. Responsibilities

• Design and implement mechanisms to harvest, filter, and utilize high-quality user signals (implicit and explicit) to iteratively improve Gemini models.

• Develop and refine reward models and critique models that accurately capture user intent and satisfaction, serving as the foundation for Reinforcement Learning from Human Feedback (RLHF) and other alignment techniques.

• Create and validate "horizontal" post-training recipes that can be robustly applied across different model sizes and modalities (including text and audio).

• Investigate novel methods for weighting, synthesizing, and selecting data to maximize the impact of user signals on model performance.

• Establish rigorous evaluation frameworks to measure the correlation between offline metrics (reward model accuracy) and online user satisfaction.

Qualifications Minimum qualifications:

• PhD in Machine Learning, natural language processing, or a related field (or equivalent practical experience).

• Experience with software development using Python and one or more deep learning frameworks (e.g., PyTorch or JAX).

• Research experience in post-training, reinforcement learning (RL), agentic RL, preference learning, or reward modeling.

• First-author (or co-author) publication in one or more peer-reviewed machine learning or natural language processing (NLP) conferences (e.g., NeurIPS, ICML, ICLR, ACL, EMNLP).

Preferred qualifications:

• First-author publications at top ML/NLP venues (NeurIPS, ICML, ICLR, ACL, EMNLP).

• Experience with modern alignment and post-training methods (e.g., RLHF, DPO, PPO, rejection sampling, or self-play).

• Experience modeling multi-turn interaction data, agent trajectories/logs, or user feedback (implicit and explicit signals).

• Experience training or evaluating reward models, critique models, or automated evaluators (e.g., LLM-as-a-judge).

• Experience in agentic post-training.