AI Infrastructure Engineer

Location: Bay Area Office, on-site

Salary: $175,000–$300,000 per year, plus potential additional compensation, equity, and benefits.

Company

hirify.global is a Silicon Valley-based 3D generative AI company building tools that transform text and images into 3D models and streamline the content creation pipeline.

What you will do

• Design, develop, and optimize the AI inference platform, including inference services, task scheduling, service orchestration, elastic scaling, and release governance.
• Build CPU/GPU resource management and scheduling systems for clusters running online inference and training workloads.
• Apply GPU technologies such as MIG, MPS, time-sharing, virtualization, and GPU partitioning in production environments.
• Improve inference throughput, latency, availability, and engineering quality across high-concurrency and multi-model pipelines.
• Design reliability, observability, disaster recovery, cost-management, and automated operations capabilities for AI infrastructure.
• Operate production infrastructure including CI/CD, build systems, deployments, and runtime environments connecting research models with product backend services.

Requirements

• Bachelor’s degree or higher in Computer Science, Software Engineering, Artificial Intelligence, Telecommunications, or a related field.
• 1–3 years of experience in backend development, infrastructure, cloud-native platforms, machine learning platforms, or AI platforms.
• Proficiency in Go or Python and strong software engineering and code-quality skills.
• Knowledge of Linux, operating systems, computer networks, and distributed systems, with the ability to resolve complex engineering issues independently.
• Practical experience with Kubernetes, Docker, microservices, or distributed systems and production system stability.
• Hands-on experience with model inference, task orchestration, resource scheduling, or service stability.

Nice to have

• Experience with GPU inference platforms, Kubernetes schedulers, device plugins, Ray, Ray Serve, model serving, or distributed inference frameworks.
• Experience with MIG, MPS, vGPU, partitioned GPUs, GPU resource reuse, observability, SRE, capacity planning, cost governance, canary deployments, or automated rollbacks.
• Open-source contributions, technical writing, personal projects, or hands-on interest in AI infrastructure, inference systems, and AI agent toolchains.

Culture & Benefits

• Work with a multidisciplinary team focused on AI, computer graphics, and 3D technology.
• Competitive salary, equity, and comprehensive health, dental, and vision insurance.
• 401(k) plan, stock options for core team members, and unlimited flexible time off.
• Flexible work environment with remote and on-site options stated among company benefits; this role is listed as on-site in the Bay Area.
• Inclusive culture emphasizing intelligence, empathy, bold innovation, quality, creativity, and collaboration.
• Fast professional growth opportunities and modern office equipment.