LLM Platform Reliability Engineer

Tribus; Hong Kong; On-site; HKD 900,000 - 1,500,000; Full time

Job summary

Tribus is seeking a Production Support Engineer to help operate the platform that provides engineers and users across the firm with access to LLMs and AI tooling. This hands-on role sits between Production Engineering, SRE and AI infrastructure, with exposure to cloud, distributed systems and LLM technologies.

You will own and troubleshoot production issues, investigate latency, support AWS/Kubernetes, build automation, and improve monitoring.

Qualifications

• Experience owning production incidents and troubleshooting in production environments.
• Experience supporting LLM/AI infrastructure OR within trading/hedge funds.
• Strong Linux and Windows knowledge.
• Scripting in Python/Bash/PowerShell.
• Experience with AWS, Kubernetes and distributed/API-driven systems.
• Monitoring/observability using Grafana/Prometheus (or similar).
• SQL experience with PostgreSQL/SQL Server or similar.
• Strong communication and incident-management skills.

Responsibilities

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

Skills

Linux

Windows

Python

Bash

PowerShell

AWS

Kubernetes

Monitoring/Observability

SQL

Tools

Grafana

Prometheus

Terraform

Ansible

Job description

Tribus is seeking a Production Support Engineer to help operate the platform that provides engineers and users across the firm with access to LLMs and AI tooling. This hands-on role sits between Production Engineering, SRE and AI infrastructure, with exposure to cloud, distributed systems and LLM technologies.

You will own and troubleshoot production issues, investigate latency, support AWS/Kubernetes, build automation, and improve monitoring.