Data Engineer for AI & RAG Pipelines

First.tech Group; Abu Dhabi; On-site; AED 350,000 - 520,000; Full time

Job summary

First.Tech is seeking a Data Engineer to join our AI team and build robust, scalable data pipelines powering Retrieval-Augmented Generation (RAG) systems and LLM applications.

You will collaborate with AI/ML engineers to deploy production-ready data workflows, optimize vector databases, and ensure data quality and freshness.

The role requires about 5 years in AI or data engineering, strong Python and SQL skills, and hands-on experience with ETL/ELT tooling and cloud storage.

Qualifications

• 5 years of relevant experience in AI/software engineering, data engineering, or MLOps
• Strong proficiency in Python and SQL
• Experience with ETL/ELT orchestration tools such as Airflow, Prefect, or Dagster
• Hands-on knowledge of vector databases such as Pinecone, Weaviate, Milvus, or FAISS
• Experience with cloud storage platforms such as AWS S3, Google Cloud Storage, or Azure Blob Storage
• Familiarity with document processing, embeddings workflows, and ANN search

Responsibilities

• Build and maintain data ingestion pipelines for structured and unstructured data.
• Design preprocessing workflows for document chunking, embeddings generation, metadata tagging, and deduplication.
• Manage and optimize vector databases to improve retrieval performance and scalability.
• Integrate data pipelines with LLM frameworks such as LangChain and LlamaIndex.
• Monitor data quality, freshness, and retrieval accuracy.
• Collaborate with AI and ML engineers to deploy and maintain production-ready RAG applications.

Skills

Python

SQL

ETL/ELT

AI/ML collaboration

Education

Bachelor’s or Master’s in CS/SE or related

Tools

Airflow

Prefect

Dagster

Pinecone

Weaviate

Milvus

FAISS

AWS S3

Google Cloud Storage

Azure Blob Storage

Job description

First.Tech is seeking a Data Engineer to join our AI team and build robust, scalable data pipelines powering Retrieval-Augmented Generation (RAG) systems and LLM applications.

You will collaborate with AI/ML engineers to deploy production-ready data workflows, optimize vector databases, and ensure data quality and freshness.

The role requires about 5 years in AI or data engineering, strong Python and SQL skills, and hands-on experience with ETL/ELT tooling and cloud storage.