Back to jobs
Job Description
- Architect high-throughput reasoning pipelines to ensure real-time ML signals are delivered in minimal time, preventing conversational lag during live calls.
- Partner with OEM leaders to scale Google’s AI protection suite to completely new user bases.
- Own the reliability of 19+ Protection-owned P0 CUIs, ensuring they meet a >99.9% reliability and latency SLO.
- Implement the client-side logic to evolve Call Screen into an intelligent, Gemini-based partner. This involves managing narrow context windows and complex memory layers for on-device Gemini Nano models.
- Lead the transition of Protection architecture from legacy stacks to modern frameworks, specifically driving Kotlin adoption and deleting technical debt to accelerate engineering velocity.