Description

Hong Kong

We're working with a leading global quantitative investment manager where technology, data and engineering are fundamental to how the business operates.

As investment in internal AI capabilities continues to grow, they're looking for a Production Support Engineer to help operate and improve the platform that provides engineers and users across the firm with access to LLMs and AI tooling.

This is a hands-on role sitting between Production Engineering, SRE and AI infrastructure, with exposure to modern cloud, distributed systems and LLM technologies.

What you'll be doing

1. Own and troubleshoot production issues across the LLM platform and model-provider integrations
2. Investigate latency, availability, API, capacity and regional performance issues
3. Support AWS/Kubernetes infrastructure and developer tooling
4. Build scripting and automation to improve diagnostics and reduce manual work
5. Improve monitoring, dashboards and alerting
6. Support releases and production changes
7. Work with engineering, infrastructure teams and external providers to resolve incidents

What we're looking for

1. Production Support, SRE or Platform Operations experience with genuine ownership of production incidents
2. Experience supporting LLM/AI infrastructure OR within trading/hedge funds
3. Strong Linux and Windows knowledge
4. Python, Bash and/or PowerShell scripting
5. AWS, Kubernetes and distributed/API-driven systems
6. Monitoring and observability -Grafana, Prometheus or similar
7. SQL experience with PostgreSQL, SQL Server or similar
8. Strong communication and incident-management skills

Useful additional experience

1. LLM gateways, inference APIs, AWS Bedrock, streaming or prompt caching
2. AI coding assistants or developer tooling
3. Terraform / Ansible
4. Multi-region production environments

A strong opportunity for an experienced Production Engineer/SRE to work closer to AI and LLM infrastructure within a highly technical quantitative investment environment.