Design and build intelligent skill discovery, hybrid routing architectures, and low-latency C++ serving components across Gemini on web, mobile, and Chrome. Pioneer dynamic system instructions, prompt representations, and semantic retrieval schemas that enable Gemini to seamlessly navigate expanding skill catalogs without attention dilution or quality regressions. Design automated evaluation frameworks (auto-raters, simulated environments, and benchmarking suites) to rigorously measure single-turn triggering precision, multi-turn tool, and parameter validity.
Perform in-depth loss analysis on production telemetry, drive iterative prompt/model hill-climbing to surpass quality thresholds, and set standards for system reliability and clean architecture across the organization. Partner closely with DeepMind Research, Search, Vertical teams (e.g., local, shopping), and external Engineering teams to onboard new modular capabilities onto the platform.
Job description provided by Google.
View the original posting
