OPEN Data Jobs is seeking a Generative AI Engineer to build production applications around foundation models and large language models, integrating retrieval-augmented generation, vector search, citations, and tool-based workflows. This hybrid role is based in Washington, United States. You will design prompts and structured outputs, evaluate grounding, safety, security, latency, and cost, and monitor applications post-release. Responsibilities include developing grounded assistants and knowledge applications with retrieval-augmented generation, drafting, summarization, classification, extraction, and transformation services exposed via user interfaces or APIs; building agents and multistep workflows with defined tool schemas, constrained permissions, approval gates, memory boundaries, replay, and exception handling; and creating evaluation systems with curated test cases, task rubrics, retrieval measures, grounding checks, safety tests, and regression thresholds. You will help establish operational pipelines for versioning prompts and configurations, comparing models, tracing execution, monitoring quality and cost, collecting feedback, and responding to incidents. You are an application engineer who can work with fast-moving model capabilities without chasing every new release, choosing architectures by evidence, making uncertainty visible, and distinguishing a compelling demonstration from a dependable service. You think in complete workflows—sources, context, models, tools, permissions, people, and failure paths—and collaborate with domain experts, data and software engi

OPEN Data Jobs is seeking a Generative AI Engineer to build production applications around foundation models and large language models, integrating retrieval-augmented generation, vector search, citations, and tool-based workflows. This hybrid role is based in Washington, United States. You will design prompts and structured outputs, evaluate grounding, safety, security, latency, and cost, and monitor applications post-release. Responsibilities include developing grounded assistants and knowledge applications with retrieval-augmented generation, drafting, summarization, classification, extraction, and transformation services exposed via user interfaces or APIs; building agents and multistep workflows with defined tool schemas, constrained permissions, approval gates, memory boundaries, replay, and exception handling; and creating evaluation systems with curated test cases, task rubrics, retrieval measures, grounding checks, safety tests, and regression thresholds. You will help establish operational pipelines for versioning prompts and configurations, comparing models, tracing execution, monitoring quality and cost, collecting feedback, and responding to incidents. You are an application engineer who can work with fast-moving model capabilities without chasing every new release, choosing architectures by evidence, making uncertainty visible, and distinguishing a compelling demonstration from a dependable service. You think in complete workflows—sources, context, models, tools, permissions, people, and failure paths—and collaborate with domain experts, data and software engi