AI Engineer
Posted Updated
Summary
Builds and deploys LLM-powered applications, AI agents, and tool-calling workflows into production, while helping shift from third-party LLM APIs to in-house/open-source hosted models. Requires 3-6 years of software engineering experience with languages like Python, Java, or Go.
We are looking for an AI Engineer to join our client`s AI team and drive the adoption of in-house and open-source LLMs across multiple business domains.
What You'll Do:
- Build and integrate AI agents, tool-calling workflows, and LLM-powered applications.
- Design and optimize prompts, evaluate model performance, and improve output quality.
- Develop and deploy AI solutions into production environments.
- Support the transition from third-party LLM APIs to internally hosted models.
- Work closely with engineering teams and business stakeholders to identify opportunities and deliver practical AI solutions.
What We're Looking For:
- 3–6 years of professional software engineering experience, including hands-on LLM application development.
- Experience building AI agents using function calling or orchestration frameworks.
- Knowledge of prompt engineering and LLM evaluation.
- Proficiency in Python, Java, Go, or similar programming languages.
- Strong problem-solving skills and a passion for applied AI.
Nice to Have:
- Japanese language proficiency.
- Experience with RAG and LLM evaluation frameworks.
- Knowledge of self-hosted LLM inference or cloud-based model deployment.
Location: Tokyo
Skills
Sign in to read and join the discussion.