Senior Software Engineer, Search Ecosystems, AI/ML

• Design and implement secure, scalable data ingestion pipelines that enforce strict access controls and copyright compliance for premium, rights-protected content across all GenAI serving surfaces.
• Optimize large-scale Retrieval-Augmented Generation (RAG) infrastructure, focusing on improving the latency, relevance, and computational efficiency of embedding generation and vector searches.
  
• Drive the end-to-end technical integration of the Expert Intelligence platform with flagship Google GenAI products (e.g., NotebookLM, Gemini Deep Research), utilizing Spanner to ensure low-latency and highly available serving.
• Develop and scale distributed batch and streaming processing pipelines (using tools like Flume) to continuously ingest, clean, and index terabytes of unstructured and semi-structured external publisher data.
  
• Provide technical leadership and mentorship to other engineers within a rapidly growing organization, guiding system architecture decisions and establishing best practices for LLM-backed infrastructure.
  

Minimum qualifications:

• Bachelor’s degree or equivalent practical experience.
  
• 5 years of experience with software development in C++ and Java
• Experience in domains related to information retrieval, search infrastructure, ranking systems, data quality, or signal extraction for content evaluation.
• Experience with large-scale data analysis, building data pipelines (e.g., Flume), and applying statistical methods to solve problems.

Preferred qualifications:

• Master's degree or PhD in Computer Science or related technical field.
  
• 5 years of experience with data structures and algorithms.
• 1 year of experience in a technical leadership role.
  
• Experience developing accessible technologies.
  

• Bachelor’s degree or equivalent practical experience.
  
• 5 years of experience with software development in C++ and Java
• Experience in domains related to information retrieval, search infrastructure, ranking systems, data quality, or signal extraction for content evaluation.
• Experience with large-scale data analysis, building data pipelines (e.g., Flume), and applying statistical methods to solve problems.