Production Support Engineer - LLM Platform

The role

You will provide day-to-day production support for QRT's platform for accessing internally hosted and external LLMs. This hands-on role focuses on incident resolution, user assistance, and established operational procedures.

What you will do

• Provide first- and second-line support for the LLM platform
• Investigate issues raised by engineering and business users
• Monitor platform health using dashboards, logs and alerts
• Troubleshoot gateway and model-provider issues
• Determine incident origin and coordinate escalation to teams or vendors
• Support coding assistants, API clients and developer workspaces
• Help users configure integrations and migrate API access
• Investigate access and model-availability queries
• Carry out operational checks for releases and configuration changes
• Maintain runbooks, troubleshooting guides and support scripts

Required qualifications

• Experience in production support, application support or platform operations
• Practical Linux troubleshooting skills
• Familiarity with Windows-based developer environments
• Working proficiency in Python, Bash and/or PowerShell
• Experience using SQL to investigate application issues, ideally in PostgreSQL
• Experience interpreting metrics, logs, traces and dashboards
• Confidence troubleshooting API-driven services
• Hands-on experience supporting LLM-based platforms or services
• Familiarity with public-cloud services, ideally AWS
• Ability to inspect containerised workloads
• Clear communication with technical and non-technical users
• Awareness of access controls, sensitive-data handling and safe diagnostic practices

Nice to have

• Experience supporting AWS Bedrock or other managed model APIs
• Experience supporting AI coding assistants, API clients or developer workspaces such as Claude Code, Codex CLI, OpenCode, PI or Coder
• Familiarity with Grafana, Coralogix or equivalent monitoring and log-analysis tools
• Exposure to LLM gateways or proxies such as LiteLLM, or internally hosted inference services such as vLLM
• Experience troubleshooting containerised services on ECS or Kubernetes
• Familiarity with identity and access provisioning, particularly Okta, SCIM and application-level permissions
• Experience supporting multi-region services and working with globally distributed support and engineering teams
• Experience coordinating support cases with cloud providers or software vendors during service degradation

Benefits

• Competitive benefits package

About the company

Qube Research & Technologies (QRT) is a global quantitative and systematic investment manager. It is a technology and data driven group implementing a scientific approach to investing.