Role Overview

KINTO Technologies is accelerating its adoption of Generative AI to transform how we build products and serve customers. As a Generative AI Engineer in our AI-First Group, you will design, develop, and deploy LLM-powered applications and AI-driven features across our mobility services.

Responsibilities

• Design and build Generative AI applications using LLMs (GPT-4, Claude, Gemini, or open-source models)
• Develop RAG (Retrieval-Augmented Generation) pipelines and vector search systems
• Build and fine-tune prompt engineering workflows
• Integrate AI capabilities into existing products via APIs and microservices
• Evaluate model performance and safety; implement guardrails
• Collaborate with product managers, engineers, and domain experts to identify AI use cases

Requirements

• Experience building production applications using LLMs or Generative AI APIs
• Proficiency in Python
• Understanding of RAG, embeddings, and vector databases (Pinecone, Weaviate, pgvector, etc.)
• Familiarity with orchestration frameworks such as LangChain or LlamaIndex
• AWS or equivalent cloud experience
• Business-level Japanese

Nice to Have

• Experience fine-tuning or deploying open-source models (Llama, Mistral, etc.)
• Knowledge of MLOps and model serving infrastructure
• Background in NLP or ML research
• English communication skills

What We Offer

• Competitive salary
• Hybrid / remote work
• Offices across Tokyo, Nagoya, Osaka, and Fukuoka
• Work at the cutting edge of AI adoption within a Toyota-group tech company