Generative AI Engineer Role

About OPEN Data Jobs

OPEN Data Jobs (ODJ) is built to craft data careers. We connect high-potential data, AI, and software professionals with meaningful work on the cutting edge of the federal sector, and our aim reaches beyond any single opening: to help you understand your strengths, find the right role, and grow throughout your career.

ODJ is organized around Roles and Openings. A Role is a durable career type, such as Data Engineer or AI Engineer: it describes the work, the skills that count, and where the path can lead. An Opening is a specific position hiring right now, with a level, a location, and an application. Roles help you see where you fit; from there, there is more than one way to move.

Today, you can apply to any Opening that fits you through our secure application system. You can also register for a Role to express interest in that broader category of work. A Role registration is not an application to every future Opening.

The work

Generative AI Engineers build production applications around foundation models and large language models. They turn model capabilities into tools for search, drafting, summarization, information extraction, multimodal work, and guided action, with the controls and evidence needed to understand how those tools behave.

The role concentrates on application and context engineering. Generative AI Engineers connect models to authoritative knowledge, tools, and workflows; design prompts and structured outputs; evaluate quality, grounding, safety, security, latency, and cost; and monitor the application after release. They treat fluent output as something to test, not proof that the system is correct.

What you'll build

· Grounded assistants and knowledge applications with retrieval-augmented generation (RAG), hybrid or vector search, citations, metadata filtering, and source-level access controls.

· Drafting, summarization, classification, extraction, and transformation services exposed through user interfaces or APIs.

· Agents and multistep workflows with defined tool schemas, constrained permissions, approval gates, memory boundaries, replay, and exception handling.

· Evaluation systems with curated test cases, task-specific rubrics, retrieval measures, grounding checks, safety and security tests, and regression thresholds.

· Operational pipelines for versioning prompts and configurations, comparing models, tracing execution, monitoring quality and cost, collecting feedback, and responding to incidents.

Who you are

You are an application engineer who can work with fast-moving model capabilities without chasing every new release. You choose architectures by evidence, make uncertainty visible, and separate a convincing demonstration from a dependable service.

You think in complete workflows: sources, context, models, tools, permissions, people, and failure paths. You collaborate with domain experts, data and software engineers, security and privacy specialists, and accountable owners to decide where generation helps and where deterministic methods or human judgment should remain in control.

What you bring

• · A strong application-engineering foundation, including programming, APIs, testing, version control, service integration, and production debugging.
• · Practical experience with foundation-model integration, prompt and context design, structured outputs, model selection, and failure analysis.
• · Working knowledge of retrieval systems, embeddings, search, knowledge stores, document ingestion, and data-access controls.
• · Evaluation discipline across answer quality, retrieval relevance, grounding, safety, security, latency, cost, and user outcomes.
• · The judgment to constrain tools and agents, design human-review paths, document limitations, and respond when production behavior changes.
• Register for Generative AI Engineer Role
• Click Apply below to register for Generative AI Engineer Role.

Requirements

What openings may require

An opening may emphasize enterprise search, document intelligence, multimodal applications, code generation, contact-center support, agent workflows, model adaptation, synthetic data, or evaluation and red-team engineering. Building or training a foundation model from scratch is not a universal requirement.

Specific openings may name a model provider, cloud platform, vector or search service, agent framework, observability stack, programming language, model-evaluation approach, content-safety service, or security and governance framework. OPEN Data Jobs will state which capabilities are required and which are preferred.