About the job
Owns moderately complex components within platform services or SDKs; leads team-level improvements to integration frameworks and developer tooling. Performs deep debugging across a bounded set of distributed services, driving fixes that protect downstream consumers and upgrade paths. Analyzes usage, performance, and error budgets for specific platform surfaces; implements targeted resilience and capacity optimizations. Authors and curates team-scoped documentation, samples, and adoption guidance.
Responsibilities
Build and operate cloud services that leverage state-of-the-art generative AI agent technologies, while also developing critical agent tool capabilities like MCP gateway, Agent Registry, and more.
Lead the effort of building distributed, scalable, high-performance generative AI agent service and agent tool platform in partnership with applied scientists and software engineers.
Investigate model structure to optimize model performance and scalability.
Build state-of-the-art systems with innovative technologies in this fast-evolving area.
Qualifications
Minimum
BS in Computer Science, or equivalent experience.
5+ years of demonstrated ability shipping scalable, cloud-native distributed systems
Ability to work in a collaborative, multi-functional team environment.
Proficient in Python, Java, and Go.
Experience with container orchestration technologies like Kubernetes.
Experience with production operations and standard processes for putting quality code in production and solve issues when they arise.
Able to optimally communicate technical ideas verbally and in writing (technical proposals, design specs, architecture diagrams and presentations).
Preferred
BS or MS in Computer Science.
Production experience with cloud computing.
Experience with generative AI agent technologies.
Experience in diagnosing, fixing and resolving issues in AI model training and serving.