LLMOps Engineer

Quick Facts

• Role: LLMOps Engineer
• Focus: Deployment, maintenance, and monitoring of LLM/GenAI solutions

Description

You will be responsible for reliable deployment, maintenance, and monitoring of solutions based on large language models. The role includes automating the LLM lifecycle and overseeing quality, cost, security, and performance. You will also build observability and auditability mechanisms and handle incidents while optimizing runtime environments and integrations.

Responsibilities

• Design and maintain deployment and monitoring processes for LLM and GenAI solutions
• Automate tests, model versioning, prompts, configurations, and evaluation datasets
• Monitor response quality, latency, availability, costs, and resource utilization
• Build mechanisms for observability, auditability, and secure access management
• Collaborate with AI engineers, architects, security, and infrastructure teams
• Handle incidents and optimize runtime environments and integrations

Requirements

• Experience in MLOps, DevOps, or maintaining AI solutions in a production environment
• Knowledge of containerization, CI/CD, APIs, cloud or on-premises infrastructure
• Practical knowledge of monitoring applications that use LLMs
• Ability to program in Python and work with code repositories
• Knowledge of data security principles, secret management, and access control
• Experience with Kubernetes and GPU environments used to run AI models
• Knowledge of networking fundamentals for GPU environments

Benefits

• MultiSport card
• Private medical care