Job Description
• Bachelor’s degree in Computer Science, Artificial Intelligence, Software Engineering, Data Science, or a related field (or equivalent practical experience).
• 2 years of experience building software with Python in a professional or serious project setting (internship plus one year is acceptable).
• Hands-on experience with LLM APIs such as OpenAI, Anthropic, or open-source models (Qwen, Llama, DeepSeek, etc.).
• Has shipped at least one AI or ML project, such as a RAG chatbot, agent, classifier, recommender, or similar end-to-end system.
• Solid fundamentals in machine learning basics, HTTP APIs, JSON, asynchronous programming, and error handling.
• Comfortable with Git, virtual environments, Docker basics, and the Linux command line.
• Able to read research papers, technical blogs, and model documentation critically, not only follow tutorials.
• Good analytical thinking, debugging ability, and attention to detail in both code and model behavior.
• Strong ownership mindset, able to take a feature from specification to production with minimal hand-holding.
• Ability to work independently as well as collaboratively with internal teams, senior engineers, and product stakeholders.
• Good written and verbal communication skills in English and Vietnamese.
Desired Qualifications:
• Experience running local LLM inference with vLLM, llama.cpp, Ollama, or similar serving stacks on GPU hardware.
• Hands-on experience with agentic orchestration frameworks such as LangGraph, CrewAI, AutoGen, or Semantic Kernel.
• Familiarity with vector databases such as Qdrant, Chroma, pgvector, FAISS, or Milvus.
• Experience with edge or embedded AI, including ONNX, TFLite, Sherpa-ONNX, or model quantization and optimization.
• Exposure to voice AI components such as ASR, TTS, wake-word detection, or real-time audio pipelines.
• Understanding of knowledge graphs, structured knowledge bases, or ontology-driven systems.
• Interest or prior work in automotive, IoT, or hardware-integrated AI applications.
• Open-source contributions, a public technical blog, or personal projects that demonstrate depth of thinking.
• If you are an ambitious AI engineer who enjoys building real products, experimenting with the latest models, and learning directly from senior engineers, we encourage you to apply.
We are looking for an AI Engineer with 2 years of experience to join our AI team in Ho Chi Minh City. You will help build production-grade intelligent systems that combine large language models (LLMs), retrieval-augmented generation (RAG), and agentic workflows. The ideal candidate has shipped at least one serious AI project, writes clean Python, and is eager to go deeper on modern LLM infrastructure, local inference, and real-world AI product development.
Key Responsibilities:
• Build LLM-powered features using LangGraph, LangChain, or equivalent orchestration frameworks, from prototype to production.
• Develop end-to-end RAG pipelines, including document ingestion, chunking, embedding, retrieval tuning, and evaluation.
• Design prompts for structured outputs using Pydantic validation, JSON mode, or function calling to ensure reliable model behavior.
• Integrate agentic workflows with tool use, multi-step reasoning, memory, and human-in-the-loop review.
• Write Python services, data pipelines, and evaluation scripts that run reliably in production environments.
• Collaborate with product, hardware, and QA teams on feature specifications, testing plans, and release reviews.
• Support local LLM deployment and inference on internal GPU servers (vLLM, llama.cpp, or similar) under senior guidance.
• Monitor model performance in production, diagnose failure modes, and iterate based on real user feedback.
• Document your work clearly, including code, prompts, evaluation results, and architectural decisions.
28:T9ba,