Senior LLMOps Engineer

About the role

PatSnap is looking for a Senior LLMOps Engineer with strong software engineering and infrastructure skills to join its Singapore team. You will lead engineering initiatives for model training, inference services and training data management, providing reliable infrastructure, supporting platforms and technical support to AI/ML and product engineering teams. This is a hands-on individual contributor role with technical leadership responsibilities.

Key responsibilities

• Lead development of model training platforms and workflows, including resource scheduling, job management and troubleshooting for training and fine-tuning workloads.
• Build and operate model inference capabilities, including open-source model deployment and external LLM API integration, with centralized access, permissions, quotas and request management.
• Build training data management capabilities, including dataset storage, versioning, quality checks, access control and traceability.
• Develop supporting platforms and automation for lifecycle management, deployment and monitoring of models, training jobs and inference services.
• Improve GPU and compute resource utilization and optimize the reliability, performance and cost of training and inference workloads.
• Take part in a team on-call rotation providing 24/7 coverage for production services, resolving incidents and driving continuous improvement.
• Collaborate with AI/ML, engineering and security teams to provide platform support and technical guidance.

Required profile

• At least 5 years of experience in software development, platform engineering, SRE or MLOps, with hands-on experience in model training or inference infrastructure.
• Familiarity with engineering workflows for model training, fine-tuning and inference, and experience deploying open-source models and integrating external LLM APIs.
• Understanding of storage, versioning and access control for training data and model artifacts.
• Fluency in English; Chinese is an advantage.

Required skills

• Strong Python programming, able to build and maintain platform services and automation tools.
• Familiarity with Linux, Kubernetes, GPU resource management, CI/CD and observability technologies.
• Proficiency with AI tools to improve engineering efficiency, and strong problem-solving and collaboration skills.
• Preferred: contributions to open-source AI infrastructure projects, and experience with distributed training, inference optimization or GPU cluster management.