Generative AI Engineer Role

Peregrine Advisors; Washington; On-site; USD 120,000 - 180,000; Full time

Job summary

Peregrine Advisors is seeking a Generative AI Engineer to build production applications around foundation models and large language models. You will connect models to knowledge, tools, and workflows, design prompts, and evaluate grounding, safety, latency, and cost while monitoring production behavior.

The role emphasizes application and context engineering, with responsibilities spanning retrieval systems, tool schemas, and end-to-end workflows in fast-moving AI environments.

Job description

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.

About OPEN Data Jobs

OPEN Data Jobs connects AI, data, and software professionals with critical roles, primarily in the federal sector. Registering with ODJ can put your profile in view for multiple positions across several clients.

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.

Compensation, benefits, work location, and employment terms are set for each specific opening and will be stated with that opening