About this role
Build distributed, fault-tolerant infrastructure that powers Anrok's AI agent capabilities—covering memory, state management, and execution for autonomous systems. Own architecture and production deployment, and build evaluation, observability, and reliability tooling to enable reliable LLM-powered agents at scale.
Skills for this role
Distributed systemsFault toleranceMemory managementState managementExecution enginesAI agentsLarge Language Models (LLMs)Prompt engineeringEvaluation frameworksRAGTool callingAgent orchestrationObservabilityReliability engineeringScalabilityPerformance optimizationSystem designProduction deploymentTestingOn-call operationsMentoring