Meggan Longoria

Agentic workflow and production-level RAG pipeline engineering designed to maximize operational efficiency and productivity.

Specializing in transforming unstructured knowledge data into high-performance Markdown schemas to maximize retrieval accuracy, eliminate token waste, and enforce strict context boundaries.

Thriving in document-driven, asynchronous environments, I enjoy working independently behind the scenes to translate operational bottlenecks into reliable, automated backend architectures.

Core Engineering Focus

• Agentic Orchestration & Tool Calling: Designing autonomous system logic, API routing, multi-agent frameworks, and Human-in-the-Loop (HITL) guardrails to ensure safe deterministic task execution.

• Data Ingestion & RAG Pipelines: Transforming messy business documentation into clean semantic chunks and Markdown layouts to optimize vector database ingestion, maximize retrieval accuracy, and eliminate model hallucinations.

• Observability & System Reliability: Implementing telemetry tracing frameworks to monitor pipeline latency, audit token consumption, and author the technical documentation required to scale stable AI deployments.

Stack & Technical Ecosystem

• Infrastructure & Orchestration: n8n, Dify, Airbyte, LangSmith, Zapier Agents

• Architectures: Retrieval-Augmented Generation (RAG), Multi-Agent Systems, Semantic Chunking

• Data & Syntax: JSON, XML, Markdown, API Integrations

Outside of that, I’m spending time with my boys and our dog, homeschooling, learning about new tools or best practices, and volunteering to ingest long-form media and transform it into optimized assets for nonprofit outreach.

Top Skills: Agentic Workflow Engineering • RAG Architecture • ETL Data Ingestion • LLM Observability • Systems Documentation