Position Overview

We are seeking a highly skilled Generative AI Engineer (or AI Solution Leader) to join our advanced technology division. The ideal candidate will have hands-on experience in LLM (Large Language Model)-based system development, Retrieval-Augmented Generation (RAG) architectures, and AI conversational agent implementation.

This position plays a crucial role in designing, prototyping, and leading the implementation of cutting-edge AI solutions that leverage knowledge graphs, vector databases, and natural language understanding to build intelligent, scalable enterprise systems.

Responsibilities

• Design and Develop Generative AI Systems
  • Build and optimize RAG architectures integrating LLMs with structured/unstructured data sources.
  • Develop knowledge graph-based information retrieval systems and implement vector search solutions (e.g., FAISS, Milvus, Pinecone, VertexAI Vector Search).
  • Research & Architecture
  • Research state-of-the-art models (e.g., GPT, Claude, Gemini, Llama) and integrate them into enterprise use cases.
  • Define the AI system architecture from data ingestion to inference and evaluation.
• AI Conversational Agent Development
  • Design and implement intelligent chatbots capable of contextual understanding and domain-specific reasoning.
  • Integrate conversational flows with backend systems and APIs.
• Project Leadership
  • Collaborate with clients and internal teams to define user requirements and translate them into technical design specifications.
  • Lead a small AI team (2–5 engineers) to execute design, implementation, and testing phases.
  • Ensure technical quality, scalability, and performance of AI-driven applications.
• Collaboration & Communication
  • Work closely with product managers, data engineers, and backend/frontend teams.
  • Contribute to proposal creation and proof-of-concept (PoC) activities for client projects.

Job Qualifications

• Core Skills
  • Hands-on experience with LLMs and RAG system design.
  • Proficiency in Python and frameworks such as LangChain, LlamaIndex, Transformers (Hugging Face), or VertexAI SDK.
  • Experience with vector databases (e.g., Pinecone, Weaviate, Milvus, Chroma).
  • Understanding of knowledge graph design and semantic search.
  • Experience building AI chatbots or conversational systems (Dialogflow, Rasa, custom LLM pipelines).
• Preferred Experience
  • Familiarity with cloud AI platforms (Google VertexAI, Azure OpenAI, AWS Bedrock).
  • Experience with MLOps, prompt engineering, or model fine-tuning.
  • Practical experience deploying LLM applications in production environments.
• Soft Skills
  • Strong analytical thinking and research capability.
  • Ability to design and lead technical projects independently.

Working time

• 8:00 AM – 12:00 PM | 1:00 PM – 5:00 PM 

Benefits

• Compensation & Well-being:
  • Probation: insurance covered
  • 13th-month salary
  • Performance & Salary review twice per year
  • 19 days of paid time off per year
  • Premium healthcare insurance for yourself and family members 
  •  Annual health check-ups.
• Career Development:
  • Sponsored certificates 
  • English course
  • Career roadmap and growth opportunities
• Dynamic working environment:
  • Free snacks in the pantry
  • Happy hour, Party celebration, Team building, Company trip,…
  • Diversified activities: Football, Badminton,…
  • Hybrid working model
  • Kozocom’s environment: happy, equal, and open-minded 

Send your CV to: nhuht@kozo-japan.com