:

We are seeking a GCP Data Engineer to design and build scalable semantic data layers from unstructured and multi-modal content such as PDFs, PowerPoint presentations, and embedded images. The role focuses on developing robust data ingestion pipelines, semantic modeling, vector-based search capabilities, and enterprise data solutions on Google Cloud Platform. Exposure to Agentic AI frameworks and orchestration is desirable but secondary.

Key Responsibilities:

- Design and develop data pipelines to ingest, process, and transform unstructured data from PDFs, PPTs, and images.

- Utilize GCP services such as Document AI, Cloud Storage, BigQuery, and Vertex AI for document and image data extraction.

- Generate and manage embeddings for semantic search and retrieval using Vertex AI and BigQuery Vector Search.

- Build and maintain semantic data models that combine structured business data with unstructured content insights.





- Develop and optimize BigQuery-based data warehouses and semantic layers for analytics and reporting.

- Orchestrate end-to-end workflows using Cloud Composer (Airflow) or GCP Workflows.

- Collaborate with business and technical teams to define semantic data structures and metadata standards.

- Support integration of semantic data platforms with Agentic AI and enterprise AI applications.

Required Skills:

- Google Cloud Platform (GCP): BigQuery, Cloud Storage, Document AI, Vertex AI.

- Solid SQL and data modeling expertise.

- Experience with unstructured document processing and multi-modal data pipelines.

- Vector databases, embeddings, and semantic search implementation.

- Workflow orchestration using Airflow/Cloud Composer.

- Knowledge of Looker, dbt, or semantic layer frameworks.

- Familiarity with Agentic AI, LangChain, Genkit, or Vertex AI Agent Builder (preferred).

📌 Gcp Data Engineer (Chennai)
🏢 Latentview
📍 Chennai