The Role<ul><li>Design and maintain scalable ML deployment and inference infrastructure.</li><li>Manage GPU-based workloads for model training and inference.</li><li>Build and optimize production pipelines for ML and LLM applications.</li><li>Improve system reliability, monitoring, and operational efficiency.</li><li>Collaborate with ML researchers and software engineers to productionize models.</li><li>Drive technical improvements and introduce new infrastructure solutio</li></ul> Your Skills <ul><li>5+ years of experience in MLOps or software engineering with substantial ML infrastructure exposure.</li><li>Hands-on experience deploying and operating ML models in production.</li><li>Strong Python, Kubernetes, and cloud infrastructure experience.</li><li>Experience with GPU computing, distributed systems, and infrastructure automation.</li><li>Understanding of system monitoring, reliability, and production operations.</li><li>Strong ownership mindset and ability to work independently.</li><li>Professional English communication skills.</li></ul> Key Highlights of the Role <ul><li>Production experience with LLMs or other generative AI models.</li><li>Experience with high-performance model serving and inference optimization.</li><li>Familiarity with GPU infrastructure, serving frameworks, and cost optimization.</li><li>Experience building ML infrastructure at scale.</li></ul> Location Tokyo Salary10 - 25 million yen Reference Number: 06940-0013536096 By clicking 'apply', you are deemed to have agreed to Robert Half Japan Privacy Notice (<a href="https://www.roberthalf.com/jp/en/privacy">https://www.roberthalf.com/jp/en/privacy</a>). Please ensure that your application documents do not include sensitive personal data such as race, beliefs, medical history, criminal record, or other information irrelevant to hiring process such as spouse or dependents. All information must be accurate and truthful, and any included hyperlinks must be safe and secure. <img src="https://counter.adcourier.com/TGluaC5EYW5nLjAzNzc4LjEwODk4QHJoaWpwLmFwbGl0cmFrLmNvbQ.gif">

Tokyo,
remote
Permanent
10.0M - 25.0M JPY / Yearly
The Role<ul><li>Design and maintain scalable ML deployment and inference infrastructure.</li><li>Manage GPU-based workloads for model training and inference.</li><li>Build and optimize production pipelines for ML and LLM applications.</li><li>Improve system reliability, monitoring, and operational efficiency.</li><li>Collaborate with ML researchers and software engineers to productionize models.</li><li>Drive technical improvements and introduce new infrastructure solutio</li></ul> Your Skills <ul><li>5+ years of experience in MLOps or software engineering with substantial ML infrastructure exposure.</li><li>Hands-on experience deploying and operating ML models in production.</li><li>Strong Python, Kubernetes, and cloud infrastructure experience.</li><li>Experience with GPU computing, distributed systems, and infrastructure automation.</li><li>Understanding of system monitoring, reliability, and production operations.</li><li>Strong ownership mindset and ability to work independently.</li><li>Professional English communication skills.</li></ul> Key Highlights of the Role <ul><li>Production experience with LLMs or other generative AI models.</li><li>Experience with high-performance model serving and inference optimization.</li><li>Familiarity with GPU infrastructure, serving frameworks, and cost optimization.</li><li>Experience building ML infrastructure at scale.</li></ul> Location Tokyo Salary10 - 25 million yen Reference Number: 06940-0013536096 By clicking 'apply', you are deemed to have agreed to Robert Half Japan Privacy Notice (<a href="https://www.roberthalf.com/jp/en/privacy">https://www.roberthalf.com/jp/en/privacy</a>). Please ensure that your application documents do not include sensitive personal data such as race, beliefs, medical history, criminal record, or other information irrelevant to hiring process such as spouse or dependents. All information must be accurate and truthful, and any included hyperlinks must be safe and secure. <img src="https://counter.adcourier.com/TGluaC5EYW5nLjAzNzc4LjEwODk4QHJoaWpwLmFwbGl0cmFrLmNvbQ.gif">
2026-11-04T02:06:18Z

Senior MLOps Engineer Job in Tokyo | Robert Half