Cookpad is looking for a Conversational AI Engineer to join our team in Japan. In this role, you will design, implement, and optimize intelligent dialogue systems that create engaging and natural user interactions, leveraging modern Large Language Models and conversational AI techniques.
What You'll Do
- Design and implement sophisticated dialogue systems that maintain context across multiple interactions.
- Develop advanced prompt engineering strategies to effectively leverage LLMs.
- Create natural, engaging conversational flows with appropriate personality and tone.
- Implement systems for intent recognition, entity extraction, and context management.
- Develop fallback mechanisms and escalation paths for ambiguous inputs and edge cases.
- Build personalization capabilities based on user preferences and history.
- Integrate conversational interfaces with backend APIs and services.
- Collaborate with front-end developers for seamless integration.
- Translate business requirements into technical conversational AI solutions.
- Take ownership of features from concept through production deployment.
- Implement production-ready code following software engineering best practices.
- Document conversation design patterns, flows, and implementation details.
- Create and maintain prompt libraries and conversation templates.
- Share conversational AI best practices with the broader engineering team.
- Communicate ideas and demos to team members effectively.
What We're Looking For
- A solid professional software engineering background with senior-level industry experience.
- Strong Python programming skills with production-level experience.
- Hands-on experience building applications with modern generative AI models (LLMs).
- Demonstrated expertise in prompt engineering and optimization for conversational AI.
- Experience designing and implementing dialogue management systems.
- Experience with multi-agent systems for complex conversational workflows.
- Experience with Retrieval-Augmented Generation (RAG) for enhancing conversational context.
- Proficiency in modern software engineering best practices (test-driven development, version control, CI/CD, containerization).
- Strong problem-solving abilities and analytical thinking, including experience exploring open-ended problems.
- Ability to work effectively both independently and within a team in a fast-paced environment.
Nice to Have
- Familiarity with vector embeddings and vector databases (e.g., Pinecone, FAISS).
- Experience with conversational AI frameworks and tools (e.g., LangChain, LlamaIndex).
- Knowledge of cloud services for AI deployment (AWS, GCP, Azure).
- Understanding of MLOps/LLMOps practices for model deployment and monitoring.
- Familiarity with UX principles for conversational interfaces.
Technical Stack
- Python
- Large Language Models (LLMs)
- Retrieval-Augmented Generation (RAG)
- Multi-agent systems
- Vector embeddings
- Vector databases (e.g., Pinecone, FAISS)
- Conversational AI frameworks (e.g., LangChain, LlamaIndex)
- Cloud services (AWS, GCP, Azure)
Benefits & Compensation
- Competitive salary
- Relocation support, including Japan work visa (if required)
- The chance to work in a fast-paced, highly ambitious team
Work Mode
This is an onsite position located in Meguro, Tokyo, Japan.
