LLM Infrastructure Engineer

The role

This role focuses on designing, deploying, and scaling the infrastructure behind model training, fine-tuning, and inference. You will work with machine learning and engineering teams to ensure models run reliably and efficiently in production.

What you will do

• 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

Required qualifications

• Proven experience building large language model infrastructure
• Hands-on experience deploying and serving machine learning models in production environments
• Strong programming skills in Python, with experience in systems or backend development
• Experience with containerization and orchestration tools such as Docker and Kubernetes
• Solid understanding of distributed systems, GPU computing, and performance optimization
• Strong written and spoken English with a clear, professional communication style
• Must have prior remote work experience
• Be fluent with remote collaboration tools and platforms (such as Slack, Zoom, Google Workspace, Asana, or similar)
• Ideally worked with US or UK-based companies

Nice to have

• Strong AWS experience, including services such as EC2, EKS, S3, and SageMaker
• Prior experience working at a large company or within enterprise-scale engineering environments
• Familiarity with LLM serving frameworks such as vLLM, TensorRT-LLM, or Triton Inference Server
• Experience with infrastructure-as-code tools such as Terraform or CloudFormation
• Experience with distributed training frameworks such as PyTorch Distributed, DeepSpeed, or Ray

Before you apply

• Applications without prior remote work experience will not be considered
• You must complete the application form in full
• You will be required to record a video
• The video is the first step of the interview process

About the company

Hire Hangar connects top talent with vetted employers, competitive pay, and real growth opportunities.