Remote AI Knowledge Engineer: RAG & LLM Systems Architect

R Systems; Singapore; On-site; SGD 90,000 - 130,000; Full time

Job summary

R Systems is seeking an AI Knowledge Engineer to develop enterprise AI knowledge solutions using LLMs, RAG, and vector databases. You will design, build, and productionize pipelines for knowledge extraction, embedding, indexing, and retrieval, collaborating with AI engineers, data scientists, and business stakeholders.

The role focuses on scalable, low-latency content processing, with emphasis on document parsing, OCR, and multimodal AI.

Qualifications

• Bachelor’s degree in CS/Engineering or related field.
• 1–3 years of data engineering or data platform development experience.
• Ability to independently build batch or streaming document processing pipelines.
• Hands-on experience with Python, PyTorch, PEFT, LoRA, OCR, VLM, LLM, prompting, Text-to-Speech, and SQL.
• Familiarity with PySpark and large-scale data processing concepts.
• Experience implementing knowledge base and RAG solutions for agentic AI use cases.
• Self-starter with problem-solving skills and attention to detail.
• Able to work independently while collaborating with engineers and stakeholders.
• Strong documentation and communication skills.

Responsibilities

• Design, build, productionize, and support scalable document parsing pipelines on a hybrid cloud platform.
• Design and implement OCR, VLM, and multimodal AI pipelines for content extraction and layout understanding.
• Develop and optimize embedding models and domain adaptation for semantic search.
• Implement knowledge ingestion, indexing, and retrieval pipelines for RAG and GenAI systems.
• Build data ingestion pipelines using Kafka, LangChain, PyMuPDF, and related tools.
• Maintain layout-aware parsing to preserve document structure and reading order.
• Extract numeric/semantic data from charts and tables with minimal hallucinations.
• Integrate pipelines with systems/files/apis/databases/streaming.
• Contribute to automation with version control and CI/CD workflows.
• Apply basic data governance and access-control policies.

Skills

Data engineering experience

Pipelines design

Python

PyTorch

PEFT

LoRA

OCR

VLM

LLM

Prompting

Text-to-Speech

SQL

Spark PySpark

RAG

Documentation

Communication

Independence

Team collaboration

Education

Bachelor’s degree in Computer Science, Engineering, or related field

Job description

R Systems is seeking an AI Knowledge Engineer to develop enterprise AI knowledge solutions using LLMs, RAG, and vector databases. You will design, build, and productionize pipelines for knowledge extraction, embedding, indexing, and retrieval, collaborating with AI engineers, data scientists, and business stakeholders.

The role focuses on scalable, low-latency content processing, with emphasis on document parsing, OCR, and multimodal AI.