Staff GenAI Evaluation Engineer

Google Inc.; Sunnyvale (CA); On-site; USD 207,000 - 301,000; Full time

Job summary

Google is seeking a Staff Software Engineer for the Vertex GenAI Evaluation Service in Sunnyvale, CA. Work on the model and agent evaluation framework, build scalable evaluation harnesses for Cloud AI LLM products, and collaborate with DeepMind Research teams to advance GenAI evaluation.

You will lead design, development, testing, deployment, maintenance, and optimization of software solutions, while guiding others and influencing product features for GenAI evaluation.

Qualifications

• Bachelor's degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience testing, and launching software products, and 3 years of experience with software design and architecture.
• 5 years of experience leading ML design and optimizing ML infrastructure (e.g., model deployment, model evaluation, data processing, debugging, fine tuning).
• 2 years of experience with GenAI techniques (e.g., LLMs, Multi-Modal, Large Vision Models) or with GenAI-related concepts (e.g., language modeling, computer vision).

Responsibilities

• Operate as a technical expert and leader within the Cloud AI Quality Evaluation team.
• Drive high-quality, scalable evaluation frameworks and tools for GenAI developers and lead features to enable seamless developer experience in each stage of GenAI evaluation.
• Develop and implement strategies for evaluation solutions to measure model and agent quality performance at scale, design infrastructure and product features of the evaluation frameworks to evaluate advanced agent features.
• Collaborate with model and agent quality teams, develop scalable systems, and ensure our evaluation workflow is efficient and provides high quality user experience.
• Engage with customers, investigate and understand product usability gaps, customer pain points, and lead GenAI research.

Skills

ML design

Model deployment

Data processing

Debugging

Fine tuning

GenAI techniques

Education

Bachelor's degree

Job description

Google is seeking a Staff Software Engineer for the Vertex GenAI Evaluation Service in Sunnyvale, CA. Work on the model and agent evaluation framework, build scalable evaluation harnesses for Cloud AI LLM products, and collaborate with DeepMind Research teams to advance GenAI evaluation.

You will lead design, development, testing, deployment, maintenance, and optimization of software solutions, while guiding others and influencing product features for GenAI evaluation.