AI Intern, GreenNode

GreenNode is the Leading AI Cloud Infrastructure and Solutions Provider in Southeast Asia, a member of VNG Group, and an official NVIDIA Cloud Partner.

With a strong understanding of the technology needs of digital-native enterprises - especially mid-tier Banks, FinTech companies, and Retail businesses, GreenNode partners closely with customers throughout their transformation journey, supporting sustainable growth and global expansion.

The AI Intern will:

• Build, and optimize RAG pipelines — including document ingestion, chunking strategies, embedding generation, and vector store management
• Experiment with and evaluate different retrieval strategies (semantic search, hybrid search, re-ranking) and chunking approaches to improve answer quality and reduce hallucinations
• Build and iterate on AI agent workflows using orchestration frameworks (e.g., LangChain, CrewAI, Agent Framework), including tool use, multi-step reasoning, and autonomous task execution
• Write, test, and refine prompts and prompt chains for both RAG systems and AI agents to ensure reliable, high-quality outputs
• Evaluate and benchmark RAG and agent systems end-to-end; identify failure modes, hallucination patterns, and propose actionable fixes
• Assist in data collection, cleaning, labeling, and preprocessing to prepare training datasets for fine-tuning tasks
• Support fine-tuning and evaluation of language models for domain-specific tasks; track experiments and report results

Education

• Currently pursuing or recently completed a Bachelor's degree in Computer Science, Data Science, AI, Software Engineering, or a related field

• Personal or academic projects involving LLMs, RAG systems, chatbots, or AI agents
• Hands-on experience calling LLM APIs (OpenAI, Anthropic, Google Gemini, or open-source models)
• Experience in fine-tune LLM
• Basic experience with vector databases or document retrieval pipelines is a plus

• Proficiency in Python; comfortable writing scripts, working with APIs, and processing data
• Familiarity with RAG components: embedding models, vector stores (Pinecone, ChromaDB, Weaviate), and retrieval strategies
• Experience with at least one agent/orchestration framework (LangChain, LlamaIndex, CrewAI, or similar)
• Understanding of prompt engineering techniques (few-shot, chain-of-thought, RAG prompting, tool use)
• Basic knowledge of ML concepts (fine-tuning, evaluation metrics, train/test splits)
• Experience with Git and collaborative development workflows
• Basic knowledge of containerization (Docker)

• Curious and self-driven learner who keeps up with the fast-moving AI landscape
• Clear communicator, able to explain technical concepts to non-technical stakeholders
• Detail-oriented with strong debugging and problem-solving skills
• Comfortable working independently while knowing when to ask for help

• Experience building end-to-end RAG applications with real-world documents
• Experience building multi-agent systems or agentic workflows in production or POC settings
• Familiarity with advanced retrieval techniques (hybrid search, re-ranking, query decomposition)