Senior / AI Data Engineer

Private Advertiser; Hong Kong; On-site; HKD 450,000 - 750,000; Full time

Job summary

Private Advertiser is seeking an experienced AI Data Engineer to design, build, and manage enterprise-grade data architecture and AI knowledge management infrastructure (Retrieval-Augmented Generation / RAG).

You will resolve data fragmentation by creating automated, scalable pipelines across a diversified portfolio, transforming unstructured assets into AI-ready knowledge bases with strong security for downstream AI systems.

Qualifications

• Minimum 3–5 years in Data Engineering or AI data pipeline development in an enterprise environment.
• Advanced proficiency in Python and data manipulation frameworks.
• Hands-on experience with unstructured data parsing libraries.
• Proven implementation experience with Vector Databases and LLM orchestration frameworks (LangChain, LlamaIndex).
• Strong expertise in SQL/NoSQL database management, RESTful API architecture, and enterprise integration patterns.
• Exceptional analytical rigor and structured problem-solving capability for data quality governance.
• Prior experience in Real Estate, Entertainment, or Retail sectors.

Responsibilities

• Architect and maintain robust ETL/ELT pipelines integrating cloud storage, local servers, and legacy enterprise systems.
• Automate extraction, parsing, and normalization of unstructured documents into structured formats for LLM ingestion.
• Deploy and optimize enterprise vector database environments.
• Implement indexing, semantic chunking, and metadata taxonomy strategies to maximize retrieval accuracy and efficiency.
• Enforce RBAC and enterprise data security protocols within the AI retrieval layer.
• Establish automated synchronization routines to monitor data repositories and update vector indices in real time.

Skills

Python

Data pipelines

ETL/ELT

SQL/NoSQL

Tools

LangChain

LlamaIndex

Vector Databases

RESTful APIs

Job description

Interested in this role? Call 52814579 to find out more.

Position Overview

We are seeking a highly skilled AI Data Engineer to design, construct, and manage our enterprise-grade data architecture and AI knowledge management infrastructure (Retrieval-Augmented Generation / RAG). Operating across our diversified portfolio, this individual will resolve data fragmentation by establishing automated, scalable pipelines.

The core focus is transforming unstructured, multi-source historical assets into clean, structured, and AI-ready knowledge bases to ensure maximum precision and security for downstream AI systems.

Job Responsibilities

Architect and maintain robust ETL/ELT pipelines integrating cloud storage (Google Workspace, Microsoft OneDrive, Cloud etc), local servers (NAS, SQL databases), and legacy enterprise systems.

Automate the extraction, parsing, and normalization of complex, unstructured business documents (PDFs, contracts, financial reports, spreadsheets) into structured formats (JSON/Markdown) optimized for Large Language Model (LLM) ingestion.

Deploy and optimize enterprise vector database environments.

Implement advanced indexing, semantic chunking, and metadata taxonomy strategies to maximize context retrieval accuracy, query efficiency, and response fidelity.

3. Data Governance & Access Management:

Enforce Role-Based Access Control (RBAC) and enterprise data security protocols within the AI retrieval layer to protect sensitive commercial intelligence.

Establish automated synchronization routines to continuously monitor data repositories and update vector indices in real time.

Job Requirement

Minimum 3–5 years in Data Engineering, Database Architecture, or AI Data Pipeline Development in an enterprise environment.

Advanced proficiency in Python and data manipulation frameworks.

Hands-on experience with unstructured data parsing libraries.

Proven implementation experience with Vector Databases and LLM Orchestration Frameworks (LangChain, LlamaIndex).

Strong expertise in SQL/NoSQL database management, RESTful API architecture, and enterprise integration patterns.

Exceptional analytical rigor, structured problem-solving capability, and a proactive approach to data quality governance.

Prior experience managing complex data environments within the Real Estate, Entertainment, or Retail sectors.

Position Overview

We are seeking a highly skilled AI Data Engineer to design, construct, and manage our enterprise-grade data architecture and AI knowledge management infrastructure (Retrieval-Augmented Generation / RAG). Operating across our diversified portfolio, this individual will resolve data fragmentation by establishing automated, scalable pipelines.

The core focus is transforming unstructured, multi-source historical assets into clean, structured, and AI-ready knowledge bases to ensure maximum precision and security for downstream AI systems.

Job Responsibilities

1. Enterprise Data Pipeline Engineering:

• Architect and maintain robust ETL/ELT pipelines integrating cloud storage (Google Workspace, Microsoft OneDrive, Cloud etc), local servers (NAS, SQL databases), and legacy enterprise systems.
• Automate the extraction, parsing, and normalization of complex, unstructured business documents (PDFs, contracts, financial reports, spreadsheets) into structured formats (JSON/Markdown) optimized for Large Language Model (LLM) ingestion.

2. Knowledge Base Architecture & RAG Optimization:

• Deploy and optimize enterprise vector database environments.
• Implement advanced indexing, semantic chunking, and metadata taxonomy strategies to maximize context retrieval accuracy, query efficiency, and response fidelity.

3. Data Governance & Access Management:

• Enforce Role-Based Access Control (RBAC) and enterprise data security protocols within the AI retrieval layer to protect sensitive commercial intelligence.
• Establish automated synchronization routines to continuously monitor data repositories and update vector indices in real time.

Job Requirement

• Minimum 3–5 years in Data Engineering, Database Architecture, or AI Data Pipeline Development in an enterprise environment.
• Advanced proficiency in Python and data manipulation frameworks.
• Hands-on experience with unstructured data parsing libraries.
• Proven implementation experience with Vector Databases and LLM Orchestration Frameworks (LangChain, LlamaIndex).
• Strong expertise in SQL/NoSQL database management, RESTful API architecture, and enterprise integration patterns.
• Exceptional analytical rigor, structured problem-solving capability, and a proactive approach to data quality governance.
• Prior experience managing complex data environments within the Real Estate, Entertainment, or Retail sectors.

For more information, contact us on 52814579 .