About this role
Build the LLM-powered systems behind 7AI security agents, including retrieval workflows, context management, agent prompts, and structured output pipelines. Work with product, platform, and backend teams to compose, optimize, and scale AI systems into production focusing on performance, cost efficiency, and reliability.
Skills for this role
LLM systemsRetrieval workflowsContext managementAgent promptsStructured output pipelinesLangChainLlamaIndexDustPrompt engineeringEvaluation metricsAPI designBackend integrationDatabase systemsCloud deploymentPythonRAGVector databasesPineconeWeaviateContext windowsCaching strategiesTool callsMulti-step reasoningMulti-modal modelsMulti-agent system designAI safety guardrailsHallucination mitigationStructured output enforcementObservabilityPerformance optimization