LLMOps Engineer (AI)

TL;DR

LLMOps Engineer (AI): Deploying, managing, and optimizing large language models in production environments with an accent on scalable GPU infrastructure and security hardening. Focus on architecting auto-scaling inference clusters, implementing LLM observability, and optimizing resource management across multi-cloud environments.

Location: Work From Home (WFH)

Company

hirify.global specializes in building scalable, secure, and high-performance GenAI systems across cloud platforms.

What you will do

• Deploy and optimize open-source large language models on cloud-based GPU instances.
• Implement rigorous security protocols for model weight storage, endpoint encryption, and prompt injection mitigation.
• Architect auto-scaling inference clusters on Azure and GCP to handle high-concurrency requests with low latency.
• Build custom observability stacks to track hallucination rates and latency for self-hosted deployments.
• Manage complex GPU scheduling and cost-optimization strategies across Azure, GCP, and AWS.

Requirements

• 3+ years of experience in LLMOps or related AI engineering roles.
• Professional experience deploying GenAI workloads on Azure and GCP.
• Deep understanding of GPU partitioning and memory-efficient inference.
• Knowledge of GenAI security, including OWASP for LLMs and secure API design.
• Experience with LLM frameworks and a capability to document system architecture clearly.

Culture & Benefits

• Remote work arrangement (Work From Home).
• Agile environment with an emphasis on rapid iteration of prompts and model parameters.
• Opportunity to work on cutting-edge GenAI production systems.