7 days ago
Base Salary
$207k - $300k/yr
Responsibilities
- Own the end-to-end architecture, roadmap, and goals for agent memory, context synthesis, graph-based cloud representation, and hybrid search/RAG systems.
- Design and implement context caching, token compression and pruning, working-memory buffers, and long-term episodic knowledge stores.
- Architect high-throughput, low-latency distributed systems and benchmarking frameworks for cloud state aggregation and retrieval quality.
- Ensure context and memory systems meet multi-tenancy, tenant isolation, compliance, and fine-grained access-control requirements.
- Partner with research and platform teams to standardize shared context models and APIs, mentor engineers, and uphold architectural review standards.
Requirements
- Bachelor’s degree in Computer Science, AI/ML, Data Systems, Information Retrieval, a related technical field, or equivalent practical experience.
- At least 8 years of software development experience.
- At least 5 years of experience testing and launching software products and 3 years of software design and architecture experience.
- At least 5 years leading ML design and optimizing ML infrastructure, including deployment, evaluation, data processing, debugging, and fine-tuning.
- At least 2 years of experience with GenAI techniques or related concepts and at least 2 years building infrastructure on cloud platforms.
- Preferred: Master’s degree or PhD in Engineering, Computer Science, or a related technical field.
- Experience with low-latency, highly available distributed storage systems and APIs on major cloud platforms.
- Expertise in agent memory, context caching, token pruning, vector search, knowledge graphs, hybrid search, graph databases, and complex cloud telemetry and topology queries.
- Ability to define roadmaps, write design documents, align stakeholders, coach engineers, and communicate complex architectures to leadership and research partners.
- Experience engineering secure, multi-tenant cloud architectures with strict data isolation and compliance controls.
Tech Stack
Google CloudGoogle Cloud Platform
Categories
About Google
A problem isn't truly solved until it's solved for all. Googlers build products that help create opportunities for everyone, whether down the street or across the globe. Bring your insight, imagination and a healthy disregard for the impossible. Bring everything that makes you unique. Together, we can build for everyone. Check out our career opportunities at goo.gle/3DLEokh