AI / LLM Engineer (RAG & Multimodal AI) (Mandarin Speakers Preferred)
Location: Malaysia
Experience: 1–4 years
Employment Type: Full-time
About the Role
We are looking for an AI / LLM Engineer with hands-on experience in building production-ready RAG and multimodal AI systems.
The ideal candidate should have experience working with LLMs, document AI, retrieval pipelines, vector databases, and multimodal workflows involving text, images, PDFs, or OCR-based systems.
This role requires practical engineering experience beyond tutorials or academic projects.
Requirements
Must Have
- Minimum 1 year of full-time experience in AI/LLM engineering
- Hands-on experience with:
- Retrieval-Augmented Generation (RAG)
- Multimodal AI / Vision-Language Models (VLMs)
- LLM application development
- Experience building or deploying:
- document AI systems
- chatbot/agentic workflows
- OCR + LLM pipelines
- semantic search systems
- AI APIs/services
- Strong Python skills
- Experience with at least some of the following:
- LangChain / LangGraph
- Vector databases (ChromaDB, FAISS, Qdrant, Pinecone, etc.)
- Open-source LLMs
- FastAPI / Flask
- Docker
- Hugging Face
- Prompt engineering
- Experience working with:
- PDFs
- images
- OCR
- embeddings
- reranking
- retrieval pipelines
- Mandarin communication skills preferred
Good to Have
- Agentic AI workflows
- GraphRAG / Knowledge Graphs
- Evaluation pipelines / hallucination detection
- GPU inference optimization
- Cloud deployment (AWS/GCP/Azure)
- CI/CD or MLOps exposure
Responsibilities
- Design and develop RAG and multimodal AI applications
- Build scalable AI pipelines for document and knowledge retrieval
- Integrate LLMs with internal systems and APIs
- Optimize retrieval quality, latency, and response accuracy
- Work on production deployment, monitoring, and evaluation of AI systems
- Collaborate with cross-functional teams to deliver enterprise AI solutions
