About this role
Build and own production AI agents and their infrastructure—design and ship agent harnesses, orchestration, evals, and model strategy on frontier LLMs. Embed with customers to integrate agent layers with WMS/TMS/ERP systems, codify repeatable deployments, and own evaluation datasets, rubrics, and experiments.
Skills for this role
PythonTypeScriptNode.jsPostgreSQLAPIsDistributed systemsPrompt engineeringPrompt tuningEvaluation frameworksModel evaluationOrchestration patternsAgent harnessesAI AgentsLLMsTool useSub-agentsRetrievalStructured outputsMCP serversProduction deploymentWMS integrationTMS integrationERP integrationTechnical design docsCustomer workshops