Google's Vertex Agent Platform team is developing an enterprise-ready agent platform to power real-world agentic use cases. This involves building a high-code agent development SDK/Kit, a managed runtime (Agent Engine) with associated services, and an inner-loop server that integrates Gemini's agentic capabilities. The team also collaborates with model quality teams and internal Google teams to upstream enterprise agentic use cases and create a cohesive platform for various agent applications.
Requirements
- 2 years of experience with software development or 1 year of experience with an advanced degree in an industry setting.
- 2 years of experience with developing large-scale infrastructure, distributed systems or networks, or experience with compute technologies, storage or hardware architecture.
- 1 year of experience with ML infrastructure (e.g., model deployment, model evaluation, optimization, data processing, debugging)
- Experience developing large-scale applications on Cloud.
- Experience on AI Agents, embedding models, in-context learning, evaluation and Open Source technologies in Generative AI space (e.g., LangChain).
- Experience with Generative AI Agents.
- Experience with Python and Java, with excellent coding skills.
Responsibilities
- Write product or system development code.
- Participate in, or lead design reviews with peers and stakeholders to decide amongst available technologies.
- Design and implement scalable, performant and compliant managed code execution sandbox service.
- Design and implement scalable, performant and compliant next-generation agent runtime services.
- Partner with quality team to evaluate and validate the agent features.
Other
- Sunnyvale, CA, USA; Kirkland, WA, USA
- Bachelor’s degree or equivalent practical experience.
- Master's degree or PhD in Computer Science or related technical fields.
