AI Engineer (Graph, RAG, LLM)

EXASOFT PTE. LTD.; Singapore; On-site; SGD 80,000 - 120,000; Full time

Job summary

A leading technology company in Singapore is seeking a Software Development Senior Analyst to architect RAG pipelines and integrate Large Language Models into enterprise solutions. The role involves designing scalable data ingestion pipelines, maintaining knowledge graphs, and collaborating with cross-functional teams to enhance AI capabilities. Ideal candidates should be proficient in Neo4j and cloud platforms like Azure. This position offers opportunities for continuous learning and impactful project engagement.

Qualifications

• Experience in architecting and implementing RAG pipelines.
• Proficiency in graph databases to support semantic reasoning.
• Ability to design scalable ingestion pipelines for diverse data types.

Responsibilities

• Architect and implement RAG pipelines including document ingestion and optimization.
• Build and maintain knowledge graphs for semantic reasoning.
• Integrate LLMs into enterprise applications with continuous improvement.

Skills

Solution Design & Development

Data Engineering & Pipelines

Model Integration & Deployment

Collaboration & Stakeholder Engagement

Tools

Neo4j

Hugging Face

Azure

Job description

Description:

POSITION OVERVIEW : Software Development Senior Analyst

1. Solution Design & Development

Architect and implement RAG pipelines, including document ingestion, chunking, embedding generation, retrieval optimization, and LLM integration.

Build and maintain knowledge graphs using graph databases (e.g., Neo4j, TigerGraph, Neptune) to support semantic reasoning, relationship mapping, and advanced query capabilities.

Develop hybrid search systems combining graph traversal, vector similarity search, and metadata-based filtering.

Optimize retrieval quality using prompt engineering, ranking algorithms, and feedback-driven improvement.

2. Data Engineering & Pipelines

Design scalable ingestion pipelines for structured, semi-structured, and unstructured data.

Implement embedding generation workflows using frameworks such as Hugging Face, LangChain, LlamaIndex, or similar.

Ensure data quality, lineage, and governance best practices within RAG and graph workflows.

3. Model Integration & Deployment

Integrate LLMs (OpenAI, Azure OpenAI, Anthropic, etc.) into enterprise applications.

Deploy solutions using cloud platforms (Azure preferred; AWS/GCP acceptable).

Implement monitoring, evaluation metrics, and continuous improvement cycles for AI systems.

4. Collaboration & Stakeholder Engagement

Work closely with product managers, architects, and cross‑functional teams to translate business needs into scalable AI capabilities.