Staff Software Engineer, Search Production Intelligence

Minimum qualifications:

• Bachelor’s degree or equivalent practical experience.
• 8 years of experience in software development.
• 5 years of experience building and developing large-scale infrastructure, distributed systems or networks, or experience with compute technologies, storage, or hardware architecture.
• Experience designing, building, and operating large-scale distributed systems, with scalability, fault tolerance, and reliability.
• Experience in software engineering, software infrastructure engineering, security, Big Data and analytics, or cloud networking.
• Experience building with LLMs, agents, tools or AI-assisted developer workflows. Experience with AI solutions with real production or operational use.

Preferred qualifications:

• 8 years of experience with data structures and algorithms.
• 3 years of experience in a technical leadership role leading project teams and setting technical direction.
• 3 years of experience working in a complex, matrixed organization involving cross-functional, or cross-business projects.
• Experience with monitoring, alerting, anomaly detection, incident management or Site Reliability Engineering (SRE) practices, including defining Service Level Indicator/Service Level Objective (SLIs/SLOs).
• Experience evaluating non-deterministic, Machine Learning (ML) or generative systems.
• Proficiency in one or more of C++, Java, Go or Python, and experience working in large production codebases.

About the job

Responsibilities

• Lead the way on reliability for Search's newest product experiences (e.g., Artificial Intelligence (AI) Mode, AI Overviews, multimodal and agentic journeys).
• Own the technical direction for one or more production intelligence areas: agentic operations, real-time feature monitoring, user-perceived reliability and reliability insights. Set a multi-quarter roadmap.
• Influence and coach a distributed team of engineers.
• Scale agentic operations across Search binaries and rotations. Author and evolve reusable skills, measure agent quality in production, and close the loop so the system gets better with every incident.
• Manage project priorities, deadlines, and deliverables. Design AI-native solutions by default. Treat Large Language Models (LLMs), agents and skills as first-class building blocks for detection, noise reduction, triage, root-causing, culprit-finding and remediation.