Forward Deployed Infrastructure Engineer

TL;DR

Forward Deployed Infrastructure Engineer (GPU Cloud): Customer benchmarking and coordination for open-access AI cloud GPU marketplace with an accent on performance tests, debugging customer trials, and optimization. Focus on designing and running benchmarks across workloads, analyzing comparisons against competitors, and maintaining benchmarking infrastructure.

Location: Remote

Company

hirify.global Labs is democratizing AI through an open-access AI cloud, aggregating global GPU resources into a marketplace and inference service.

What you will do

• Act as technical point-of-contact for customer trials, running standardized and custom benchmarks.
• Design, run, and analyze performance tests across customer workloads, including comparisons to AWS, Lambda, and others.
• Debug and optimize issues in GPU utilization, NCCL setup, container configs during trials.
• Create clear reports and documentation from benchmark results for easy handoffs.
• Maintain scripts, containers, and environments for benchmarking across SKUs.
• Identify performance gaps, optimize cluster configs, and collaborate with supply and engineering teams.

Requirements

• Experience running infra performance tests or ML model benchmarks (training, inference, or both).
• Strong knowledge of GPU cloud infra, workloads, bottlenecks, and config impacts.
• Clear and fast written communication for reports, docs, and handoffs.
• Ability to juggle multiple trials/projects simultaneously.
• Familiarity with GPU cloud providers (AWS, Lambda, CoreWeave, Runpod, etc.).

Nice to have

• Prior customer-facing experience in a startup or devtools setting.
• Background as an ML engineer, solutions architect, or technical account manager.

Culture & Benefits

• Equal opportunity employer committed to diversity and inclusive environment.
• Fast-scaling Series A startup led by AI/Math/CS PhD co-founders.
• Focus on building customer trust through technical credibility and reliable delivery.