Enterprise AI Engineer - Remote in Canada, Production-Ready

Quix; EE. UU.; A distancia; USD 110.000 - 180.000; Jornada completa

Descripción de la vacante

Quix seeks an experienced AI/LLM engineering lead to transform AI capabilities into dependable enterprise workflows that align with data, systems, and governance requirements. You will guide model selection, build retrieval-based applications, and evaluate behavior to ensure responsible, production-ready deployments.

You will collaborate with data and engineering teams to ground outputs in organizational information, implement safeguards, and document system behavior for both technical and

Formación

• Proven experience delivering production AI or LLM applications beyond prototypes.

Responsabilidades

• Build AI-assisted workflows that connect to enterprise data, APIs, and operational systems.
• Develop retrieval-augmented generation pipelines that ground model responses in relevant organizational information.
• Create evaluation methods for output quality, reliability, and behavior at system boundaries.
• Add safeguards such as access controls, content filtering, audit records, and output validation.
• Work with data and engineering partners to establish dependable inputs and integrations.
• Document system behavior, limitations, and operating needs for technical and nontechnical audiences.
• Compare hosted AI services and open models against use-case needs and risk considerations.

Conocimientos

Production AI/LLM apps

Retrieval systems

Model evaluation

Enterprise data integration

AI governance & controls

Herramientas

Vector stores

Embeddings

Semantic search

Reranking

Descripción del empleo

Quix seeks an experienced AI/LLM engineering lead to transform AI capabilities into dependable enterprise workflows that align with data, systems, and governance requirements. You will guide model selection, build retrieval-based applications, and evaluate behavior to ensure responsible, production-ready deployments.

You will collaborate with data and engineering teams to ground outputs in organizational information, implement safeguards, and document system behavior for both technical and