About this role
Lead design and implementation of Datadog's LLM Observability product, building features to monitor, trace, evaluate, and debug LLM and generative AI systems in production. Work cross-functionally with engineering, product, UX, and applied science to prototype, scale, and influence architecture for observability of AI workloads.
Skills for this role
Large Language Models (LLMs)Generative AILLM ObservabilityDrift detectionModel evaluationBehavior tracingDistributed systemsScalable backend architecturesInference pipelinesModel internalsPrompt engineeringDebugging LLMsObservability tools/platformsPrototypingCross-functional collaborationMentoring