LLM Infrastructure Engineer (Fully Remote)

Hire Hangar, Inc.; United States; Remote; USD 150,000 - 230,000; Full time

Job summary

Hire Hangar, Inc. is seeking an engineer to design and maintain scalable infrastructure for LLM workloads, including GPU management and performance tuning.

You will deploy low-latency inference services, optimize throughput, and ensure reliability across production systems, with a strong emphasis on cost efficiency and automated deployments.

Qualifications

• Proven experience with LLM infrastructure and production ML systems.
• Strong Python, distributed systems, and container orchestration with Docker and Kubernetes.
• Prior remote work experience and familiarity with US/UK companies.

Responsibilities

• Design and maintain infrastructure for LLM workloads; manage GPU compute and optimize utilization.
• Deploy inference services with focus on latency, throughput, and reliability.
• Automate deployments with IaC and CI/CD; implement monitoring and cost optimization.

Skills

Python

Distributed systems

Cloud infrastructure

Tools

Docker

Kubernetes

CI/CD

IaC

Job description

• Build and scale infrastructure for LLM training, fine-tuning, and inference.
• Work with ML and engineering teams to ensure reliable, efficient production systems.

Key Responsibilities:

• Design and maintain infrastructure for LLM workloads; manage GPU compute and optimize utilization.
• Deploy inference services with focus on latency, throughput, and reliability.
• Automate deployments with IaC and CI/CD; implement monitoring and cost optimization.

Required Qualifications:

• Proven experience with LLM infrastructure and production ML systems.
• Strong Python, distributed systems, and container orchestration with Docker and Kubernetes.
• Prior remote work experience and familiarity with US/UK companies.