Master's degree in Computer Science, Machine Learning, AI, Mathematics, or related field, or equivalent experience.
Research experience in LLM post-training, reinforcement learning, multilingual benchmarking, reasoning, or foundation model training.
Experience in training, post-training, or evaluating foundation models.
Ability to translate research ideas into practical improvements across teams.
Strong communication and collaboration skills with a passion for human languages and user-centric AI.
Responsibilities
Drive research in post-training, reinforcement learning, and agentic modeling to enhance Gemini's performance across languages.
Develop algorithms for cross-lingual capability transfer and synthetic data generation.
Enhance cultural grounding, factuality, and consistency in multimodal interactions.
Design evaluation methodologies and reward signals for complex model behaviors.
Collaborate with Gemini teams and product partners to implement research breakthroughs into flagship models.
Benefits
20% bonus target
Equity benefits
Comprehensive health and wellness programs
Generous paid time off
Opportunities for professional development and growth.
Full Job Description
Minimum qualifications:
Master's degree in Computer Science, Machine Learning, Artificial Intelligence, Mathematics, or a related technical field, or equivalent practical experience.
Experience with research in one or more of the following areas: LLM post-training and alignment, reinforcement learning, multilingual benchmarking, reasoning and agentic systems, or foundation model training.
Experience training, post-training, or evaluating foundation models.
Preferred qualifications:
Ability to translate open-ended research ideas into landed improvements in frontier models across multi-team collaborations.
Excellent communication and collaboration skills, and a genuine passion for human languages and building AI that works for people everywhere.
Responsibilities
Drive an ambitious research agenda in post-training, reinforcement learning, and agentic modeling to improve Gemini's reasoning, tool use, factuality and multimodal performance across global languages, dialects, and locales.
Develop scalable algorithms for cross-lingual capability transfer, synthetic data generation, reward modeling, and self-improvement flywheels that close the quality gap for both major global languages and low-resource languages.
Improve local and cultural grounding, factuality, naturalness, and language consistency across long-horizon multi-turn and multimodal interactions (text, speech, image, and video).
Design trustworthy evaluation methodologies, evaluations, and human-grounded reward signals to measure and steer complex agentic and culturally nuanced model behaviors.
Partner closely with core Gemini post-training, agentic, and pretraining/mid-training teams-as well as product partners across Google-to land research breakthroughs directly into flagship Gemini models.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training.
Google is a multinational technology company that specializes in Internet-related services and products. These include online advertising technologies, search engine, cloud computing, software, and hardware. Google was founded in 1998 by Larry Page and Sergey Brin while they were Ph.D. students at Stanford University. The company has grown tremendously since then and has become one of the most valuable companies in the world. Google's mission is to organize the world's information and make it universally accessible and useful.
