Remote Data Engineer – AI Grounding & RAG on GCP

Globant; Mexico; Remote; MXN 600,000 - 1,000,000; Full time

Job summary

Globant is seeking a mid-level Data Engineer focused on AI grounding and RAG within Google Cloud. You will build and maintain scalable data pipelines, ensure data quality, and collaborate with stakeholders to implement retrieval-augmented generation solutions using Vertex AI/LangChain.

The role emphasizes hands-on data engineering, Python and SQL expertise, and experience with vector databases and data governance in a remote setup spanning Mexico.

Qualifications

• 3 to 5 years of experience in Data Engineering and pipeline development.
• Extensive experience designing and maintaining automated ETL/ELT data pipelines for both structured and unstructured enterprise data (knowledge bases, FAQs, manuals, ticketing logs).
• Strong expertise within Google Cloud Platform (GCP), especially BigQuery and Cloud Storage.
• Proven hands-on experience with pipeline orchestration tools such as Dataflow (Apache Beam) or Cloud Composer (Apache Airflow).
• Advanced proficiency in Python and complex SQL for large-scale data manipulation and extraction.
• Practical experience with data chunking, tokenization, and embedding strategies to support enterprise knowledge retrieval.
• Experience implementing and maintaining vector search solutions, particularly Vertex AI Vector Search.
• Solid understanding of Retrieval-Augmented Generation (RAG) architectures and frameworks (such as LangChain) integrated with Gemini Enterprise models.
• Experience collaborating directly with client data owners to establish data quality, freshness cycles, governance, and strict privacy boundaries.

Skills

Python

SQL

Data Engineering

ETL/ELT pipelines

GCP

BigQuery

Vertex AI Vector Search

RAG

LangChain

Data governance

Tools

BigQuery

Cloud Storage

Dataflow

Cloud Composer

LangChain

Vertex AI Vector Search

Job description

Globant is seeking a mid-level Data Engineer focused on AI grounding and RAG within Google Cloud. You will build and maintain scalable data pipelines, ensure data quality, and collaborate with stakeholders to implement retrieval-augmented generation solutions using Vertex AI/LangChain.

The role emphasizes hands-on data engineering, Python and SQL expertise, and experience with vector databases and data governance in a remote setup spanning Mexico.