info_outline
X Applicants in San Francisco: Qualified applications with arrest or conviction records will be considered for employment in accordance with the San Francisco Fair Chance Ordinance for Employers and the California Fair Chance Act.Note: By applying to this position you will have an opportunity to share your preferred working location from the following:
Mountain View, CA, USA; New York, NY, USA; San Francisco, CA, USA.
Minimum qualifications: - Bachelor's degree in Cognitive Science, Human-Computer Interaction (HCI), Linguistics, a related field, or equivalent practical experience.
- 6 years of experience in conversation design, content design, with equivalent experience designing for conversational AI/LLMs.
- include a portfolio, website, or any other relevant link to your work in your resume (providing a viewable link or access instructions).
Preferred qualifications: - Experience in interaction design, particularly managing mixed tactile/voice entry points and mid-conversation modality switching.
- Experience in guiding cross-functional teams through ideation, validation, and iteration processes, transforming abstract ideas into shippable, user-centered model behavior.
- Experience in vibe-coding and developing AI-powered prototypes.
- Familiarity with behavioral data and strong capability to utilize user signals and lifecycle data to create data-driven designs, while being equally capable of moving forward in the absence of data.
- Excellent communication and collaboration skills with the ability to articulate positions, and challenge cross-functional partners with rigorous model UX principles.
About the jobIn this role, you will shape the evolution of Gemini's mobile experience on Floaty, turning it into a seamless, contextual, and highly listenable assistant. As a key member of the Gemini App Model UX team, you will collaborate with product managers, engineers, and research scientists to solve unique multimodal and voice issues for a highly visible representative experience of Gemini. You will work directly with Google's advanced AI models to build real-world solutions that refine talk tracks, optimize dynamic responses, and manage complex multi-modal context switching. Your work will ensure that every model response feels intuitive, glanceable, and reliable, driving meaningful engagement and quality improvements for millions of users on-the-go.
Individual pay is determined by factors including job-related skills, experience, and relevant education or training. US: $159000 - $231000 (USD) 15% bonus target equity benefits Learn more about benefits at Google .
Responsibilities - Specify the ideal conversational structures, query categorization logic, and underlying interaction patterns that bring voice, text, and multimodal entry points to life.
- Implement advanced system instructions (SIs) that optimize dynamic responses based on user signals and device capabilities.
- Apply systems thinking to deliver flexible solutions that scale across a range of devices.
- Initiate qualitative assessments of model performance, establishing principle-based rubrics to drive continuous quality hillclimbing across core user journeys (CUJs).
- Partner with AI product designers to craft leading-edge multimodal solutions, ensuring model responses, device signals, and screen relevancy work in concert to deliver cohesive, glanceable experiences.
