AI/ML Engineer – LLM Applications
[…] is seeking a talented and driven mid-level AI/ML Engineer to join our team in Norco, CA supporting a large Navy program. In this role, you will design, develop, and evaluate AI-enabled applications built on large language models (LLMs), including retrieval-augmented generation (RAG) and multi-step agentic workflows. You will build data ingestion and retrieval pipelines, integrate LLMs with enterprise data sources and tools, and implement controls to improve system safety, reliability, and output quality.
This position supports deployment in secure, on-premises environments and requires clear documentation to support accreditation and traceability.
As with any position, additional expectations include: meeting deadlines, communicating regularly with assigned supervisors, attending required meetings, and completing other duties as assigned.
Responsibilities
Responsibilities• Design, develop, and maintain LLM-based applications, including RAG solutions and multi-step agentic workflows.• Develop data ingestion, document processing, embedding, and retrieval pipelines.• Integrate LLMs with enterprise data sources, APIs, and downstream tools using tool or function calling and structured outputs.• Implement safety controls, input and output validation, and quality checks to support reliable system behavior.• Build evaluation datasets and testing processes to measure retrieval accuracy, response quality, and overal