AI Agent Engineer
<p data-start="108" data-end="230"><strong data-start="143" data-end="155">Location</strong>: Tokyo<br data-start="162" data-end="165" /><strong data-start="162" data-end="172">Salary</strong>: ¥11,856,000 annual<br data-start="188" data-end="191" /><strong>Reference Number</strong>:06940-0013272619</p><hr data-start="232" data-end="235" /><h3 data-start="237" data-end="263">Position Overview:</h3><p data-start="264" data-end="560">We are looking for a skilled LLM Agent Engineer to join our AI team. In this role, you will drive the development and optimization of intelligent agent systems, focusing on improving agent performance, enhancing observability, and refining evaluation pipelines through data-driven approaches.</p><h3 data-start="562" data-end="591">Key Responsibilities:</h3><ul data-start="592" data-end="1507"><li data-start="592" data-end="715"><p data-start="594" data-end="715">Agent Performance Monitoring: Improve monitoring systems for AI agents to ensure optimal performance and reliability.</p></li><li data-start="716" data-end="834"><p data-start="718" data-end="834">LLM Evaluation Pipelines: Design and implement evaluation pipelines and benchmarks tailored to LLM applications.</p></li><li data-start="835" data-end="948"><p data-start="837" data-end="948">Operational Support: Resolve operational issues, ensuring continuous system stability and high performance.</p></li><li data-start="949" data-end="1066"><p data-start="951" data-end="1066">Iterative Agent Improvement: Lead the enhancement of LLM agents based on performance metrics and user feedback.</p></li><li data-start="1067" data-end="1193"><p data-start="1069" data-end="1193">Agile Practices: Actively contribute to daily scrums, sprint planning, and sprint reviews. Reporting will be in English.</p></li><li data-start="1194" data-end="1303"><p data-start="1196" data-end="1303">Documentation: Maintain clear documentation of services and models for internal teams and stakeholders.</p></li><li data-start="1304" data-end="1404"><p data-start="1306" data-end="1404">Collaboration: Engage in daily communication through Slack and meetings, primarily in English.</p></li><li data-start="1405" data-end="1507"><p data-start="1407" data-end="1507">Code Reviews: Ensure high engineering standards through thorough documentation and code reviews.</p></li></ul><h3 data-start="1509" data-end="1541">Required Qualifications:</h3><ul data-start="1542" data-end="1937"><li data-start="1542" data-end="1650"><p data-start="1544" data-end="1650">Experience in LLM Agent development, particularly with frameworks like LangChain or LangGraph.</p></li><li data-start="1651" data-end="1751"><p data-start="1653" data-end="1751">Proven track record in developing AI/LLM evaluation pipelines and performance measurement systems.</p></li><li data-start="1752" data-end="1841"><p data-start="1754" data-end="1841">Strong background in software engineering, emphasizing maintainable and clean code.</p></li><li data-start="1842" data-end="1937"><p data-start="1844" data-end="1937">A data-driven mindset, with the ability to analyze and act on metrics to improve performance.</p></li></ul><h3 data-start="1939" data-end="1972">Preferred Qualifications:</h3><ul data-start="1973" data-end="2221"><li data-start="1973" data-end="2049"><p data-start="1975" data-end="2049">Familiarity with MCP (Model Context Protocol) or similar technologies.</p></li><li data-start="2050" data-end="2136"><p data-start="2052" data-end="2136">Knowledge of statistics and data science for advanced modeling and analysis.</p></li><li data-start="2137" data-end="2221"><p data-start="2139" data-end="2221">Experience with Databricks for data processing and machine learning workflows.</p></li></ul><p><em>By clicking 'apply', you give your express consent that Robert Half may use your personal information to process your job application and to contact you from time to time for future employment opportunities. For further information on how Robert Half processes your personal information and how to access and correct your information, please read the Robert Half privacy notice <a href="https://www.roberthalf.com/jp/en/privacy">https://www.roberthalf.com/jp/en/privacy</a>. Please do not submit any sensitive personal data to us in your resume (such as such as race, beliefs, social status, medical history or criminal record) as we do not collect your sensitive personal data at this time.</em></p><hr /><p>お客様が「今すぐ応募」ボタンをクリックすることにより、ロバート・ハーフ(以下、当社)がお客様の応募内容を処理し、求人情報を今後随時ご連絡する目的で個人情報を使用することに明示的に同意ただいたこととなります。当社による個人情報の処理方法、またお客様自身の個人情報へのアクセスおよびその訂正に関する詳細については、プライバシー規約(<a href="https://www.roberthalf.com/jp/ja/privacy">https://www.roberthalf.com/jp/ja/privacy</a>)をお読みください。当社は、要配慮個人情報はお預かりしておりませんので人種、信条、社会的身分、病歴、犯罪の経歴など、取扱いに特に配慮を要する個人情報は、ご提出いただく職務経歴書・レジュメ等に含めないようお願いいたします。</p><img src="https://counter.adcourier.com/V2lsbC5GaXRjaC44NDA4MC4xMDg5OEByaGlqcC5hcGxpdHJhay5jb20.gif">
- Tokyo,
- remote
- Contract
-
11.9M - 11.9M JPY / Yearly
- <p data-start="108" data-end="230"><strong data-start="143" data-end="155">Location</strong>: Tokyo<br data-start="162" data-end="165" /><strong data-start="162" data-end="172">Salary</strong>: ¥11,856,000 annual<br data-start="188" data-end="191" /><strong>Reference Number</strong>:06940-0013272619</p><hr data-start="232" data-end="235" /><h3 data-start="237" data-end="263">Position Overview:</h3><p data-start="264" data-end="560">We are looking for a skilled LLM Agent Engineer to join our AI team. In this role, you will drive the development and optimization of intelligent agent systems, focusing on improving agent performance, enhancing observability, and refining evaluation pipelines through data-driven approaches.</p><h3 data-start="562" data-end="591">Key Responsibilities:</h3><ul data-start="592" data-end="1507"><li data-start="592" data-end="715"><p data-start="594" data-end="715">Agent Performance Monitoring: Improve monitoring systems for AI agents to ensure optimal performance and reliability.</p></li><li data-start="716" data-end="834"><p data-start="718" data-end="834">LLM Evaluation Pipelines: Design and implement evaluation pipelines and benchmarks tailored to LLM applications.</p></li><li data-start="835" data-end="948"><p data-start="837" data-end="948">Operational Support: Resolve operational issues, ensuring continuous system stability and high performance.</p></li><li data-start="949" data-end="1066"><p data-start="951" data-end="1066">Iterative Agent Improvement: Lead the enhancement of LLM agents based on performance metrics and user feedback.</p></li><li data-start="1067" data-end="1193"><p data-start="1069" data-end="1193">Agile Practices: Actively contribute to daily scrums, sprint planning, and sprint reviews. Reporting will be in English.</p></li><li data-start="1194" data-end="1303"><p data-start="1196" data-end="1303">Documentation: Maintain clear documentation of services and models for internal teams and stakeholders.</p></li><li data-start="1304" data-end="1404"><p data-start="1306" data-end="1404">Collaboration: Engage in daily communication through Slack and meetings, primarily in English.</p></li><li data-start="1405" data-end="1507"><p data-start="1407" data-end="1507">Code Reviews: Ensure high engineering standards through thorough documentation and code reviews.</p></li></ul><h3 data-start="1509" data-end="1541">Required Qualifications:</h3><ul data-start="1542" data-end="1937"><li data-start="1542" data-end="1650"><p data-start="1544" data-end="1650">Experience in LLM Agent development, particularly with frameworks like LangChain or LangGraph.</p></li><li data-start="1651" data-end="1751"><p data-start="1653" data-end="1751">Proven track record in developing AI/LLM evaluation pipelines and performance measurement systems.</p></li><li data-start="1752" data-end="1841"><p data-start="1754" data-end="1841">Strong background in software engineering, emphasizing maintainable and clean code.</p></li><li data-start="1842" data-end="1937"><p data-start="1844" data-end="1937">A data-driven mindset, with the ability to analyze and act on metrics to improve performance.</p></li></ul><h3 data-start="1939" data-end="1972">Preferred Qualifications:</h3><ul data-start="1973" data-end="2221"><li data-start="1973" data-end="2049"><p data-start="1975" data-end="2049">Familiarity with MCP (Model Context Protocol) or similar technologies.</p></li><li data-start="2050" data-end="2136"><p data-start="2052" data-end="2136">Knowledge of statistics and data science for advanced modeling and analysis.</p></li><li data-start="2137" data-end="2221"><p data-start="2139" data-end="2221">Experience with Databricks for data processing and machine learning workflows.</p></li></ul><p><em>By clicking 'apply', you give your express consent that Robert Half may use your personal information to process your job application and to contact you from time to time for future employment opportunities. For further information on how Robert Half processes your personal information and how to access and correct your information, please read the Robert Half privacy notice <a href="https://www.roberthalf.com/jp/en/privacy">https://www.roberthalf.com/jp/en/privacy</a>. Please do not submit any sensitive personal data to us in your resume (such as such as race, beliefs, social status, medical history or criminal record) as we do not collect your sensitive personal data at this time.</em></p><hr /><p>お客様が「今すぐ応募」ボタンをクリックすることにより、ロバート・ハーフ(以下、当社)がお客様の応募内容を処理し、求人情報を今後随時ご連絡する目的で個人情報を使用することに明示的に同意ただいたこととなります。当社による個人情報の処理方法、またお客様自身の個人情報へのアクセスおよびその訂正に関する詳細については、プライバシー規約(<a href="https://www.roberthalf.com/jp/ja/privacy">https://www.roberthalf.com/jp/ja/privacy</a>)をお読みください。当社は、要配慮個人情報はお預かりしておりませんので人種、信条、社会的身分、病歴、犯罪の経歴など、取扱いに特に配慮を要する個人情報は、ご提出いただく職務経歴書・レジュメ等に含めないようお願いいたします。</p><img src="https://counter.adcourier.com/V2lsbC5GaXRjaC44NDA4MC4xMDg5OEByaGlqcC5hcGxpdHJhay5jb20.gif">
- 2025-09-04T04:28:26Z