AI Automation Engineer

Job Title: AI Automation EngineerWorking Type: Full Time | On-siteLocation: Ho Chi Minh CityAbout GloGlo is a digital wellness platform making movement, mindfulness, and mental well-being accessible and sustainable. We are expanding into new areas like yoga therapy, coaching, and sleep, and building a Growth Team to drive user acquisition, engagement, and retention.OverviewThe position targets an engineer capable of designing and maintaining end-to-end AI-powered automation systems. Key areas include Natural Language Processing (NLP),vector databases (Qdrant), GPT integrations, and structured data management.You will be responsible for building intelligent pipelines that automate contentunderstanding, transformation, and generation through RAG (Retrieval-AugmentedGeneration)-based architectures and structured JSON workflows.Key Responsibilities• Develop AI automation pipelines involving NLP, metadata extraction, and structureddata storage.• Integrate speech-to-text, translation, and summarization models.• Use GPT APIs to generate content (summaries, documents, responses, reports etc.).• Manage embeddings and metadata using JSON + Qdrant vector database for semanticretrieval.• Connect GPT agents to Qdrant to enable context-aware RAG workflows.• Implement LangChain-based chains for prompt templating and controlled contextmanagement.• Write automation scripts in Python for data processing, API integration, and taskscheduling.• Reduce API costs via prompt optimization, structured JSON pre-processing, andcaching strategies.• Manage AI workflows within Dockerized local environments for consistency andscalability.Required Skills and Experience• Python: scripting, data processing, API usage.• Linux (Ubuntu/Debian): shell scripting, package management, system setup.• Qdrant vector database: schema design, embedding indexing, semantic searchimplementation.• RAG frameworks & LangChain: prompt chains, retriever-reader patterns, memorycontext linking.• Docker: Build and deploy isolated AI containers.• Structure modular environments to avoid version conflicts.• Coordinate multi-container setups for AI workflows.• Ability to clone and run projects from books or GitHub repositories.• Familiarity with core AI libraries: NumPy, Pandas, PyTorch, TensorFlow.• Vector databases: experience with Qdrant (preferred), Milvus, or Pinecone for semanticembedding storage and retrieval.• Monitoring AI pipelines via Grafana and Kibana dashboardsNice to Have• Ability to visualize AI outputs through frontend dashboards or lightweight UI tools.• GraphQL knowledge for structured query integrations.• FastAPI experience for custom GPT endpoint deployment.• Prompt Engineering and advanced structured prompt design (JSON schema-driven).• Context Engineering, Memory Engineering, State History Engineering, and CNL-Ptechniques for adaptive conversation flows and vibe-coded outputs.• Familiarity with AI APIs (OpenAI, Anthropic, MCP or similar LLM providers).• Knowledge of Semantic Search and Retrieval-Augmented Generation (RAG)optimization strategies.