AI Infrastructure Engineer (AI Performance Optimization)

Location: 100% remote within the United States

Salary: $100,000–$150,000 annually

Company

hirify.global is a technology consulting and software development company delivering cloud, AI, data, and enterprise solutions across the United States.

What you will do

• Optimize training and inference workloads for large neural network systems to maximize throughput, minimize latency, and reduce cost.
• Improve performance across the full stack, from low-level kernels and memory management to distributed systems and compiler-level optimization.
• Apply profiling, instrumentation, measurement, debugging, and analytical methods across CPU, GPU, and distributed environments.
• Optimize deep learning and production-scale LLM inference workloads on modern GPUs.
• Collaborate with product, design, engineering, operations, and business stakeholders to translate requirements into production-ready solutions.
• Contribute through code reviews, design reviews, and mentorship of junior engineers.

Requirements

• Bachelor’s or master’s degree in computer science, computer engineering, or a related field.
• 6+ years of experience in performance engineering, ML systems, or HPC.
• Strong proficiency in Python and C++.
• Hands-on experience optimizing deep learning workloads on modern GPUs and understanding distributed training and inference.
• Knowledge of model compression, memory hierarchies, communication primitives, parallelism strategies, and profiling tools.
• Applicants must be authorized to work in the United States; new H-1B visa petitions cannot be sponsored.

Nice to have

• Experience with vLLM, TensorRT-LLM, DeepSpeed, Triton, or CUTLASS.
• Experience with FinOps for AI workloads.
• Publications or talks on AI systems performance.

Culture & Benefits

• Full-time direct W-2 employment.
• Opportunity for career growth within an established technology organization.
• Cross-functional collaboration across product, design, engineering, operations, and business teams.