Software Engineer, Applied AI, Model Quality
New York, NY, USA · Full-time · Posted Oct 20, 2026
- Experience
- 5 years in software development; 3 years testing, maintaining, or launching software products; 1 year in software design and architecture. Preferred: 5 years in an ML field and 5 years in ML design and infrastructure; 3 years in complex cross-functional projects.
- Education
- Bachelor’s degree or equivalent practical experience.
About the job
Build evaluation systems and tools to measure and improve the quality of image-understanding and generative AI models used in Google Workspace.
What you'll do
- Build human-powered and LLM-powered automated systems to evaluate model performance and establish metrics for grounding, coherence, safety, and helpfulness.
- Run evaluations across models and datasets, and provide actionable findings to improve model quality with research and cross-functional teams.
- Create tools and systems that make model evaluation more efficient.
What they ask for
- Bachelor’s degree or equivalent practical experience.
- 5 years of experience with software development in one or more programming languages.
- 3 years of experience testing, maintaining, or launching software products.
- 1 year of experience with software design and architecture.
Nice to have
- Master's degree or PhD in Computer Science or related technical field.
- Experience in an ML field, ML design or infrastructure, complex cross-functional projects, or integrating generative AI tools or LLM interfaces into workflows.
Pay
$174000 - $252000 (USD) base salary
Tools
Large Language Model (LLM), GemPix, Gemini
AI focus
Evaluate and improve generative AI and image-understanding model quality, including metrics for grounding, coherence, safety, and helpfulness.
Model-written summary · the original posting is authoritative