Senior GenAI Knowledge Architect for Enterprise RAG

AVENSYS CONSULTING PTE. LTD.; Singapore; On-site; SGD 180,000 - 280,000; Full time

Benefits offered by this job

Bonus potential

Health insurance

Performance bonuses

Job summary

Avensys Consulting Pte Ltd is seeking a Senior AI Knowledge Engineer to drive production-grade GenAI and knowledge-platform solutions in an enterprise setting. You will design RAG pipelines, ingestion workflows, embeddings, and secure retrieval while integrating LLMs and AI agents with existing knowledge systems.

The role requires deep hands-on experience with vector databases, knowledge graphs, semantic search, and Python-based API services.

Qualifications

• Strong hands-on experience building production enterprise RAG and AI knowledge platforms.

Responsibilities

• Build enterprise GenAI, RAG, AI Agent and knowledge retrieval solutions.
• Develop RAG pipelines, document ingestion, chunking, embeddings, vector/semantic/hybrid search.
• Integrate LLMs and AI agents with enterprise knowledge systems.
• Build and optimize vector databases, knowledge graphs and semantic search.
• Develop Python APIs/microservices and production AI services.
• Implement secure, permission-based knowledge retrieval, grounding and hallucination mitigation.
• Monitor and evaluate retrieval accuracy, relevance, groundedness and response quality.

Skills

Python

LLMs

GenAI

RAG

LangChain

LangGraph

LlamaIndex

Semantic Kernel

Azure AI Search

Pinecone

Qdrant

Weaviate

FAISS

Elasticsearch

Embeddings

Vector Search

Semantic Search

OpenAI

Azure OpenAI

AWS Bedrock

Vertex AI

Neo4j

RDF

SPARQL

REST APIs

SQL

NoSQL

Git

Tools

Azure AI Search

Pinecone

Qdrant

Weaviate

FAISS

Elasticsearch

LangChain

LangGraph

LlamaIndex

Semantic Kernel

Neo4j

RDF

SPARQL

Job description

Avensys Consulting Pte Ltd is seeking a Senior AI Knowledge Engineer to drive production-grade GenAI and knowledge-platform solutions in an enterprise setting. You will design RAG pipelines, ingestion workflows, embeddings, and secure retrieval while integrating LLMs and AI agents with existing knowledge systems.

The role requires deep hands-on experience with vector databases, knowledge graphs, semantic search, and Python-based API services.