Job Description
We are looking for a AI Engineer to lead the development and deployment of LLM-based chatbot systems that solve real-world business problems.
As a core member of our AI team, you will:
Responsibilities
- Build advanced AI-driven chatbot systems using large language models (LLMs) such as GPT-4, Claude, or Gemini.
- Design and implement pipelines for tasks like question answering, knowledge retrieval (RAG), and customer support.
- Collaborate closely with product, backend, and frontend teams to integrate LLMs into production systems.
- Define evaluation strategies and benchmarks tailored to specific business domains (e.g., sales, customer service).
- Stay up to date with the latest advancements in generative AI, LLMs, prompt engineering, and semantic search.
You will play a key role in shaping and scaling AI-powered solutions across our organization.
Requirements
- 1-4 years of experience in AI/ML-related roles (e.g., AI Engineer, Machine Learning Engineer, Data Scientist).
- Hands-on experience applying commercial LLMs (e.g., OpenAI, Claude, Gemini) to real-world applications such as chatbots, RAG systems, or virtual assistants.
- Strong understanding of LLM evaluation techniques (e.g., LLM-as-a-Judge) and experience designing benchmarks for domain-specific use cases (e.g., sales, support).
- Proficient in Python and experienced in building LLM pipelines via APIs.
- Solid understanding of AI system architecture: prompt orchestration, API integration, vector store usage, and input/output pipelines.
- Clear and effective communication skills; able to work cross-functionally with engineering and product teams.
- Comfortable working in modern development environments: Git, Docker, Linux, and cloud platforms (preferably AWS).
Nice to have:
- Experience with open-source tools such as Hugging Face Transformers, Ollama, Llama.cpp, Lang Chain, or Llama Index.
Contact information
- Email: [Confidential Information]
- Phone/Zalo: 083 2019 403
