Senior LLMOps Engineer

Patsnap; Singapore; On-site; SGD 120,000 - 180,000; Full time

Job summary

PatSnap in Singapore is seeking a Senior LLMOps Engineer with strong software engineering and infrastructure skills to join PatSnap’s Singapore team. You will lead development of training platforms, inference services, and data management, delivering reliable infrastructure and support to AI/ML and product teams.

This hands-on, individual contributor role combines technical leadership with practical implementation across training pipelines, deployment, monitoring, and 24/7 on-call coverage to

Qualifications

• 5+ years in software development, platform engineering, SRE or MLOps with hands-on training/inference infra.
• Strong Python programming for building and maintaining platform services.
• Experience deploying open-source models and integrating external LLM APIs.
• Familiar with Linux, Kubernetes, GPU resource management, CI/CD and observability.

Responsibilities

• Lead the development of model training platforms and workflows, including scheduling and job management.
• Build and operate model inference capabilities with centralized access, permission, quota 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 reliability, performance, and cost of workloads.
• Participate in a team on-call rotation providing 24/7 coverage for production services.
• Collaborate with AI/ML, engineering, and security teams to provide platform support and technical guidance.

Skills

Python programming

Platform engineering

SRE / MLOps

Kubernetes

CI/CD

Observability

GPU resource management

Tools

Git

Terraform

Docker

Job description

Job Description

We are looking for a Senior LLMOps Engineer with strong software engineering and infrastructure skills to join PatSnap’s Singapore team.

Job Description

We are looking for a Senior LLMOps Engineer with strong software engineering and infrastructure skills to join PatSnap’s 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, contributing directly to the company’s AI transformation.

Key Responsibilities

• Lead the development of model training platforms and workflows, supporting resource scheduling, job management, and troubleshooting for training and fine-tuning workloads.
• Build and operate model inference capabilities, covering open-source model deployment and external LLM API integration, with centralized access, permission, quota, 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.
• Participate in a team on-call rotation providing 24/7 coverage for supported production services, resolve incidents, and drive continuous improvement.
• Collaborate with AI/ML, engineering, and security teams to provide platform support and technical guidance, enabling AI adoption across the company.

Job Requirements

• At least 5 years of experience in software development, platform engineering, SRE, or MLOps, with hands-on experience in model training or inference infrastructure.
• Strong Python programming skills, with the ability to independently develop and maintain platform services and automation tools.
• Familiarity with engineering workflows for model training, fine-tuning, and inference, with experience deploying open-source models and integrating external LLM APIs.
• Familiarity with Linux, Kubernetes, GPU resource management, CI/CD, and observability technologies.
• Understanding of storage, versioning, and access control for training data and model artifacts.
• Proficiency in using AI tools to improve engineering efficiency, with strong technical judgment, problem-solving, and cross-team collaboration skills.
• Fluency in English; Chinese language proficiency is an advantage.

Preferred Qualifications

• Contributions to open-source projects related to AI infrastructure, model training, or inference tooling.
• Experience with distributed training, inference performance optimization, or GPU cluster management.