Senior AI Compute Infrastructure Engineer (Web3)

TL;DR

Senior AI Compute Infrastructure Engineer (Web3): Designing and operating GPU and accelerator clusters for model training, inference, and experimentation with an accent on scalability, reliability, and cost efficiency. Focus on optimizing inference pipelines, building scheduling and orchestration systems, and ensuring production-grade GPU utilization across heterogeneous environments.

Location: Remote (Must be based in the United States)

Salary: $127.2k – $254.4k

Company

hirify.global is a mission-focused crypto exchange dedicated to accelerating the global adoption of blockchain technology and financial inclusion.

What you will do

• Own and operate GPU and accelerator clusters for training, inference, evaluation, and experimentation.
• Design infrastructure to run models locally on GPUs to reduce dependency on external providers and contain costs.
• Build and improve scheduling, orchestration, placement, and quota management across heterogeneous environments.
• Optimize inference pipelines for latency and throughput using vLLM, Triton Inference Server, or TensorRT.
• Develop observability for GPU utilization, memory pressure, token throughput, and capacity spend.
• Evaluate and integrate new hardware, specialized accelerators, and serving frameworks.

Requirements

• 5+ years of infrastructure engineering experience with a focus on GPU compute, ML infrastructure, or distributed systems.
• Hands-on experience operating GPU clusters in production, including orchestration and cost optimization.
• Strong systems engineering fundamentals across Linux, networking, containers, and Kubernetes.
• Proficiency in Python for infrastructure automation and operational workflows.
• Experience with ML serving frameworks such as vLLM, Triton, TensorRT, or KServe.
• Must be based in the United States.

Nice to have

• Experience at frontier AI labs, hyperscalers, or high-frequency trading firms.
• Familiarity with specialized accelerators like TPUs, AWS Trainium, or Gaudi.
• Experience with distributed training frameworks such as DeepSpeed, Megatron-LM, or Ray.
• Proficiency in Rust, C++, Go, or CUDA for performance-critical infrastructure.
• Experience in crypto, financial services, or security-sensitive production environments.

Culture & Benefits

• Fully remote work environment.
• Competitive base salary with Bonus and Equity programs.
• Wellness allowance.
• Comprehensive medical, dental, and vision insurance (US only).
• 401(k) retirement plan.