Trình độ

• Yêu cầu

  <Must>
  - Bachelor's degree in Information Technology or Japanese (preferably with experience studying or working in Japan).
  - Minimum 2-3 years of experience in the same roles.
  - Proficiency in Python and SQL.
  - Ability to customize and extend low-code platforms (e.g., Dify, N8N).
  - Experience with vector databases and search techniques (e.g., Weaviate, Pinecone, FAISS, Milvus).
  - Experience designing and implementing RAG pipelines (e.g., multi-source retrieval, reranking, metadata-driven search).
  - Experience fine-tuning or adapting LLMs (LoRA, prompt engineering).
  - Experience with text data processing (preprocessing, metadata tagging, feature extraction, embeddings).
  - Experience working with GPT-based and open-source LLMs (e.g., OpenAI, LLaMA, Mistral).
  - Experience deploying on cloud platforms (e.g., Azure, GCP, AWS).
  - Strong understanding of SaaS integration and hybrid system architecture.
  - Fluent in English
  
  <Prefers>
  - Experience with search and retrieval systems (e.g., Azure AI Search, Elastic, or hybrid search solutions).
  - Understanding of LLM orchestration and product workflows (e.g., multi-step pipelines, chatbot architecture).
  - Familiarity with LLM evaluation/testing frameworks (e.g., Ragas, Promptofoo).
  - Experience with MLOps practices for LLM (model lifecycle, monitoring, drift detection).
  - Experience with CI/CD pipelines (e.g., GitHub Actions).
  - Experience with monitoring and logging systems (e.g., Sentry, Grafana).

• Tiếng Anh

  Doesn’t matter

• Ngôn ngữ khác

  None