Apply on Employer Site

Google DeepMind · 10 hours ago

Research Scientist, Model Collaborativity

Seattle, WA

Full-time

Hybrid

Senior Level

$166K/yr - $291K/yr

Google DeepMind is a team of scientists, engineers, and machine learning experts dedicated to advancing artificial intelligence for public benefit and scientific discovery. They are seeking a Research Scientist to enhance Gemini's collaborative capabilities through advanced reinforcement learning methods, focusing on user interaction and satisfaction.

Artificial Intelligence (AI)Business DevelopmentFoundational AIMachine Learning

Growth Opportunities

Responsibilities

Design and implement novel multiturn RL algorithms to train collaborative LLMs. This includes exploring advanced methods for credit assignment, model robustness, and exploration/exploitation strategies

Develop and scale our training infrastructure, building on our existing framework for training against stateful user simulators

Formalize the problem of collaborativity by creating new metrics, environments, and evaluation methodologies that capture long-term user satisfaction and preference alignment

Do cutting-edge research that pushes the boundaries of how agents learn from interactions with users, user simulators and other agents with diverse model behaviors

Collaborate with research and product teams to integrate these capabilities into core Gemini products, improving tasks that require sustained interaction and user understanding

Qualification

Reinforcement LearningMachine LearningPythonDeep Learning FrameworksData AnalysisLarge-scale ML SystemsNatural Language ProcessingGame TheoryUser SimulatorsAcademic Publications

Required

PhD in Machine Learning, Reinforcement Learning, Natural Language Processing, or a related field

Strong data analysis and synthetic data generation skills

Strong development skills in Python and experience with deep learning frameworks like JAX, PyTorch, or TensorFlow

Experience building and working with large-scale ML training systems

Preferred

Deep theoretical and practical experience in Reinforcement Learning (e.g., policy gradient methods, value-based methods, model-based RL, credit assignment, robustness)

Experience developing and training large generative models (LLMs)

Strong track record of academic publications in top-tier conferences (e.g., NeurIPS, ICML, ICLR, AAAI)

Familiarity with research on game theory, multi-agent systems, or learning from human feedback (RLHF/RLAIF)

Experience building or using user simulators for RL training

Benefits

Bonus

Equity

Benefits

Company

Google DeepMind

Glassdoor4.5

Google DeepMind aims to research and build safe artificial intelligence system to solve intelligence and advance science and humanity. It is a sub-organization of Google.

Founded in 2010