Software Engineer, AI Compute Infrastructure (AI)

TL;DR

Software Engineer, AI Compute Infrastructure (AI): Building and scaling the foundational compute infrastructure for generative video models with an accent on GPU optimization and high-throughput data pipelines. Focus on designing scalable job frameworks, implementing distributed computing systems using Ray and Kubernetes, and optimizing CUDA kernels for model performance.

Location: Los Angeles, Palo Alto, San Francisco, Toronto, or Singapore

Company

hirify.global is an AI company dedicated to making visual storytelling accessible through state-of-the-art generative video technology.

What you will do

• Optimize GPU and cluster utilization across thousands of devices for inference, training, and large-scale deployment of video generation models.
• Build highly scalable frameworks for managing heterogeneous compute jobs and multi-modal data ingestion.
• Develop world-class observability, tracing, and visualization tools to diagnose performance bottlenecks.
• Collaborate with AI researchers to integrate acceleration techniques such as custom CUDA kernels into production pipelines.
• Manage and optimize cloud and container infrastructure using Kubernetes and Ray for elastic scaling.

Requirements

• 5+ years of full-time industry experience in large-scale MLOps, AI infrastructure, or HPC systems.
• Strong proficiency in Python and a high-performance language such as C++.
• Deep hands-on experience with orchestration and distributed computing frameworks like Kubernetes and Ray.
• Experience with core ML frameworks including PyTorch, TensorFlow, or JAX.
• Proficiency with data frameworks such as Ray, Apache Spark, or LanceDB.
• Bachelor's degree in Computer Science, Engineering, or a related field.

Nice to have

• Master's or PhD in Computer Science or a related technical field.
• Demonstrated Tech Lead experience driving projects from conceptual design to production.
• Prior experience building infrastructure specifically for Generative AI models (diffusion, GANs, or LLMs).
• Expertise in GPU acceleration and low-level compute programming (CUDA, NCCL).
• Background in operating large-scale data infrastructure managing petabytes of multi-modal data.

Culture & Benefits

• Competitive salary and comprehensive benefits package.
• Dynamic and inclusive work environment.
• Opportunities for professional growth and career advancement.
• Collaborative culture that values innovation and creativity.
• Access to the latest technologies and tools.