Generative AI Inference Engineer

TL;DR

Generative AI Inference Engineer (AI): Develop and optimize multi-modal generative AI inference systems with an accent on diffusion model architectures and high-performance computing. Focus on designing scalable inference pipelines, model tuning, deployment, and collaboration with cloud providers to deliver hosted AI solutions.

Location: Remote (United States)

Company

hirify.global is a leading company specializing in generative AI technologies and high-performance computing for creative AI applications.

What you will do

• Lead design and development of customer-facing multi-modal ML inference systems.
• Collaborate with Platform and Inference teams on optimization, tuning, and deployment of next-generation models.
• Partner with cloud providers to deliver hosted inference solutions.
• Drive business impact through strategic machine learning initiatives.
• Prototype and productionize inference platform improvements and new features.

Requirements

• Location: Must be based in the United States or able to work remotely within the US
• 7+ years experience in productionizing machine learning systems and inference pipelines.
• Expertise in python services, pytorch, and high-performance inference frameworks.
• Deep understanding of diffusion architectures and GPU profiling tools.
• Experience with cloud orchestration (Kubernetes) and cloud providers (AWS, GCP, Azure).
• Strong communication and collaboration skills.