Job Summary
This position focuses on advancing research in post-training methodologies such as Reinforcement Learning (RL) and Super Fine-Tuning (SFT) aimed at improving personalization. The role also encompasses the creation of innovative evaluation frameworks to assess model quality effectively. Furthermore, the engineer will be responsible for the design and training of agents that manage tools and APIs, ensuring hyper-personalized user experiences.
Responsibilities
- Conduct research to advance post-training techniques, emphasizing RL and SFT for enhanced personalization.
- Develop and implement novel evaluation frameworks to rigorously assess the quality of models.
- Design and train agents that effectively orchestrate tools and APIs for delivering customized user experiences.
Qualifications
- Bachelor’s degree in a relevant field.
- A minimum of 5 years of experience in the design and deployment of evaluation frameworks.
- Preferred experience in agentic memory research.
- Experience training models in environments that utilize accelerators is also advantageous.
Google provides equal employment opportunities to all employees and applicants for employment and prohibits discrimination and harassment of any type without regard to race, color, religion, age, sex, national origin, disability status, genetics, protected veteran status, sexual orientation, gender identity or expression, or any other characteristic protected by federal, state or local laws.
