About this role
Evaluate frontier models and transform promising advances into production agent systems, owning the lifecycle from rapid prototyping through launch, monitoring, and iteration. Improve agent planning, tool use, context management, and build secure, observable, and reliable agent systems while collaborating with PM, Data Science, and Research.
Skills for this role
PythonGoRustPostgreSQLDynamoDBAWSTypeScriptLarge Language Models (LLMs)Machine LearningAgent SystemsModel EvaluationPrompt EngineeringContext EngineeringTool IntegrationBrowser AutomationLong-running Task ExecutionProduction MonitoringObservabilityTracing and ReplayPermissions and SafeguardsDistributed SystemsBackend ServicesData Analysis