Senior AI Operations Engineer
RemoteChina or Singapore
Job Summary
Build Operations RAG knowledge bases using open-source frameworks by integrating incident documentation and inspection guidelines. Utilize Python to integrate with monitoring and logging systems, implementing AI-driven alert correlation, noise reduction, and duplicate suppression. Develop lightweight AI Agents based on Function Calling and MCP for automated execution of low-risk operational tasks. Create time-series analysis scripts to predict resource utilization trends for server workloads and disk usage. Manage the containerized deployment, monitoring, version upgrades, and day-to-day maintenance of AI Operations services. Requires a Bachelor's degree, 5+ years in software development or system operations, Python proficiency, and Microsoft certifications. Occasional infrequent in-person activity may be required.
Required Qualifications
- Bachelor's degree or above in Computer Science, Software Engineering, Artificial Intelligence, Automation, or related disciplines
- Minimum 5 years of experience in software development, cloud computing, system operations, platform engineering, or related technical fields
- Solid understanding of Microsoft technologies, architectures, and associated operating principles
- Proven experience in cloud service deployment, administration, monitoring, optimization, and troubleshooting
- Proficiency in Python programming and script development
- Strong knowledge of Linux and Windows Server administration and operations
- Hands-on experience with containerization technologies such as Docker and Kubernetes
- Familiarity with monitoring platforms, log analysis tools, and IT automation solutions
- Understanding of Large Language Model (LLM) applications and AI technologies, including RAG, AI Agents, MCP, and related operational use cases
- Must hold at least two Microsoft certifications
- Occasional infrequent in person activity may be required
Hiring someone like this?
Get your role in front of qualified candidates on Sorce.