Remote LLM Infrastructure Engineer - Scale GPU Models

OpenKrill; United States; Remote; USD 140,000 - 210,000; Full time

Job summary

Hire Hangar is seeking an LLM Infrastructure Engineer to design, deploy, and scale the infrastructure behind model training, fine-tuning, and inference. This remote, US-time-zone role collaborates with ML and software teams to ensure reliable, cost-effective production workloads.

You will manage GPU resources, build data pipelines, implement monitoring and CI/CD, and optimize for latency and throughput. Strong Python, Docker/Kubernetes, and cloud experience are essential to move models from

Qualifications

• Proven experience building large language model infrastructure in production.
• Hands-on experience deploying ML models in production environments.
• Strong Python programming skills for systems/backend development.
• Experience with Docker and Kubernetes.
• Excellent written and spoken English; remote-work experience required.

Responsibilities

• Design, build, and maintain infrastructure for training, fine-tuning, and serving large language models
• Deploy and scale LLM inference services with a focus on latency, throughput, and reliability
• Manage GPU compute resources and optimize workload scheduling and utilization
• Build and maintain data pipelines that support model training and evaluation
• Implement monitoring, logging, and alerting for model performance and system health
• Optimize infrastructure costs while maintaining performance and availability
• Automate deployment workflows using infrastructure-as-code and CI/CD practices
• Collaborate with ML engineers and researchers to move models from experimentation into production
• Proactively identify bottlenecks, investigate root causes, and resolve infrastructure issues

Skills

Python programming

Distributed systems

Remote collaboration

English communication

Tools

Docker

Kubernetes

Terraform

CloudFormation

PyTorch

LLM serving frameworks

CI/CD tooling

AWS

Slack

Zoom

CI/CD pipelines

Job description

Hire Hangar is seeking an LLM Infrastructure Engineer to design, deploy, and scale the infrastructure behind model training, fine-tuning, and inference. This remote, US-time-zone role collaborates with ML and software teams to ensure reliable, cost-effective production workloads.

You will manage GPU resources, build data pipelines, implement monitoring and CI/CD, and optimize for latency and throughput. Strong Python, Docker/Kubernetes, and cloud experience are essential to move models from