AI Infrastructure Engineer: GPU ML Inference & Scale

Next Frontier Capital; Albuquerque (NM); On-site; USD 130,000 - 210,000; Full time

Job summary

Hoonify is seeking an AI Infrastructure Engineer to design, build, and operate production-grade LLM inference infrastructure. You will optimize GPU-backed workloads, implement robust services, and collaborate with senior engineers to deliver scalable, observable systems.

You will work on multi-GPU, multi-node deployments, profiling across vLLM, SGLang, and TensorRT-LLM, and contribute to runbooks and design notes for the team.

Qualifications

• Bachelor’s degree in CS/CE/Applied Math/Data Science or equivalent.
• 3+ years of relevant software engineering experience.
• Experience with ML systems, GPU workloads, or high-performance backend services.

Responsibilities

• Deploy, tune, and optimize high-performance LLM inference pipelines on GPU infra.
• Profile and optimize model serving workloads across frameworks and hardware.
• Build scalable production API services for model inference with observability.
• Develop benchmarking, monitoring, and automation tooling for measurable performance.
• Scale workloads across multi-GPU, multi-node clusters.
• Collaborate with engineering and product teams to align infra capabilities with services.
• Write runbooks and design notes; participate in reviews.

Skills

Kubernetes

Python

LLMs

Linux

CI/CD

Go/Rust/C++

Education

Bachelor’s degree in CS/CE/Applied Math/Data Science

Tools

vLLM

SGLang

TensorRT-LLM

Git

CI/CD Pipelines

Job description

Hoonify is seeking an AI Infrastructure Engineer to design, build, and operate production-grade LLM inference infrastructure. You will optimize GPU-backed workloads, implement robust services, and collaborate with senior engineers to deliver scalable, observable systems.

You will work on multi-GPU, multi-node deployments, profiling across vLLM, SGLang, and TensorRT-LLM, and contribute to runbooks and design notes for the team.