Job Description

Edison Smart is supporting a fast-growing global technology business that is continuing to invest heavily in its AI and machine learning capabilities.

We are looking for a Senior LLMOps Engineer to take ownership of key infrastructure across LLM training, inference and data management.

This is a hands-on engineering position suited to someone who combines strong software engineering with MLOps/platform expertise and has experience building infrastructure that supports production AI systems.

The Role

You will work closely with AI/ML and engineering teams to build and improve the platforms used to train, deploy and operate large language models at scale.

Responsibilities will include:

• Build and improve infrastructure for LLM training, fine-tuning and inference.
• Develop platforms for training job management, resource scheduling and model lifecycle management.
• Deploy and operate open-source LLMs alongside integrations with external model APIs.
• Build centralised capabilities around model access, permissions, quotas and request management.
• Develop training data infrastructure covering storage, versioning, quality, access control and traceability.
• Improve GPU utilisation and optimise the performance, reliability and cost of AI workloads.
• Build automation around model deployment, monitoring and infrastructure operations.
• Troubleshoot complex production and infrastructure issues.
• Participate in an on-call rotation supporting production AI services.
• Work closely with AI/ML, engineering and security teams to support wider adoption of AI across the organisation.

What We're Looking For

• 5+ years across Software Engineering, Platform Engineering, SRE, MLOps or AI Infrastructure.
• Strong Python engineering skills.
• Hands-on experience with model training, fine-tuning and/or inference infrastructure.
• Experience deploying open-source LLMs and integrating third-party LLM APIs.
• Strong Linux and Kubernetes knowledge.
• Experience working with GPU infrastructure or compute-intensive workloads.
• CI/CD and observability experience.
• Understanding of model and dataset storage, versioning and access control.
• Strong understanding of production engineering principles including scalability, reliability and performance.
• Comfortable operating as a senior individual contributor while providing technical leadership across teams.
• Fluent English.

Nice to Have

• Distributed model training experience.
• LLM inference optimisation.
• GPU cluster management.
• Contributions to open-source AI infrastructure or MLOps projects.
• Experience operating AI/ML platforms at significant scale.
• Chinese language capability.