AI Engineer — Agents & LLMs

Focus: Agentic Systems · LLMs · Fine-Tuning · Evaluation · Data Pipelines Languages: Japanese required (business level); business-level English or Mandarin also required

About the role

We are looking for an AI Engineer to join our team and build the next generation of autonomous AI Agents. In this role, you will design and build intelligent systems capable of reasoning, planning, and executing complex workflows.

This is a key role in the growing AI team at Gazai. You will help develop the AI innovations that deliver value to our customers and shape our long-term AI roadmap, working closely with our software engineering and product teams to bring these innovations to life.

Responsibilities

• Leverage state-of-the-art agentic frameworks (e.g. LangChain/LangGraph, AutoGen, CrewAI) and tailor them for Gazai use cases
• Deploy agents on a scalable and reliable backend
• Continuously build and add new capabilities to Gazai’s agents — including new tools, skills, and MCP servers
• Optimize agent serving for latency, reliability, and cost
• Build evaluation frameworks to measure agent quality and reliability
• Build and maintain data pipeline operations
• Fine-tune models for storytelling and conversational chat in Japanese
• Stay up to date with the latest advancements in agents and LLMs

Qualifications

• 3+ years of professional ML / AI / software engineering experience, with at least 1 year working on agentic and/or LLM-based applications
• Experience with agentic frameworks such as LangChain/LangGraph, AutoGen, CrewAI, or custom-built architectures
• Experience building custom agent tools, skills, and MCP servers
• Experience with LLM APIs and/or open-source / open-weight LLMs
• Conceptual understanding of how LLMs work — architecture, training, inference
• Strong software engineering skills and proficiency in Python
• Eagerness to stay current on the latest AI developments; fast learner
• Japanese required (business level); business-level proficiency in English or Mandarin also required

Bonus — you will stand out if…

• You have experience training LLMs (pre-training and/or post-training)
• You have a strong understanding of foundational ML, deep learning, and AI model architectures
• You have research publications in AI
• You have experience with vector databases such as Pinecone, Chroma, or Qdrant