Freelance Retrieval Augmented Generation Jobs in Utah

Design and execute validation strategies for AI/ML and Retrieval-Augmented Generation (RAG) features, including model quality, grounding, and safety evaluation. Major Responsibilities or Assigned ...

Architect, manage, and scale vector search infrastructure (e.g., Pinecone, Milvus, Qdrant, Weaviate, pgvector) for high-performance semantic search and retrieval-augmented generation (RAG) pipelines.

Architect, manage, and scale vector search infrastructure (e.g., Pinecone, Milvus, Qdrant, Weaviate, pgvector) for high-performance semantic search and retrieval-augmented generation (RAG) pipelines.

Architect, manage, and scale vector search infrastructure (e.g., Pinecone, Milvus, Qdrant, Weaviate, pgvector) for high-performance semantic search and retrieval-augmented generation (RAG) pipelines.

... retrieval-augmented generation pipelines using enterprise data sources • Build and orchestrate agent-based workflows to automate targeted tasks • Integrate LLM APIs such as Anthropic Claude and ...

Design and manage vector databases and embedding pipelines to support semantic search and Retrieval-Augmented Generation (RAG). * Build and optimize retrieval pipelines including hybrid search ...

Develop Retrieval-Augmented Generation (RAG) solutions and AI agents that enable continuous monitoring of competitor activity, customer trends, market signals, and regulatory developments. * Build ...

Architect the retrieval-augmented generation (RAG), Data Graph, GraphRAG layer so LLM responses are grounded in a well defined Ontology with trusted definitions and edges so live operational ...

Architect the retrieval-augmented generation (RAG), Data Graph, GraphRAG layer so LLM responses are grounded in a well defined Ontology with trusted definitions and edges so live operational ...

Familiarity with retrieval augmented generation (RAG) pipelines and how search quality feeds downstream LLM applications. * Background in information retrieval, natural language processing

Familiar with RAG (Retrieval-Augmented Generation) pipelines, vector databases, or orchestration frameworks. * Capable of working with GraphQL, microservices, or event-driven systems in fast-paced ...

Experience building both traditional machine learning models (e.g., regression, classification, clustering) and generative AI systems (e.g., LLMs, retrieval-augmented generation, prompt engineering)

Strong understanding of modern AI systems, including agent architectures, tool use, retrieval-augmented generation (RAG), AI evaluations, and the tradeoffs between quality, latency, reliability, and ...

Strong understanding of modern AI systems, including agent architectures, tool use, retrieval-augmented generation (RAG), AI evaluations, and the tradeoffs between quality, latency, reliability, and ...

Strong understanding of modern AI systems, including agent architectures, tool use, retrieval-augmented generation (RAG), AI evaluations, and the tradeoffs between quality, latency, reliability, and ...

Strong understanding of modern AI systems, including agent architectures, tool use, retrieval-augmented generation (RAG), AI evaluations, and the tradeoffs between quality, latency, reliability, and ...

Knowledge of modern artificial intelligence frameworks including retrieval-augmented generation, vector databases, orchestration frameworks, and observability tools * Familiarity with emerging ...

Experience building both traditional machine learning models (e.g., regression, classification, clustering) and generative AI systems (e.g., LLMs, retrieval-augmented generation, prompt engineering)

AI/ML background: intelligent document processing (IDP), OCR, NLP, RAG (retrieval-augmented generation), vector databases, or ML model training and deployment (MLOps) . * Cloud experience ( Azure ...

... retrieval-augmented generation (RAG) pipelines with vector databases for domain-specific Q&A. • Experience with Azure AI Foundry and Azure AI capabilities like document intelligence, computer ...