Forward Deployed Infrastructure Engineer
Core
Bridge the gap between infrastructure suppliers and technical customers by validating performance, running benchmarks, and ensuring delivered compute resources match customer expectations.
Role type
Forward Deployed Infrastructure Engineer (Performance Validation & Customer Trials)
Builds
GPU marketplace and AI inference service platform
Domain
Cloud Infrastructure / AI Compute / GPU Hardware
Deliverable
production ML models | product features | dashboards & analysis
Required skills
GPU cloud infrastructure knowledge, performance benchmarking design and execution, debugging GPU utilization and NCCL setups, container configuration management, technical reporting and documentation, multi-project coordination
Preferred skills
Customer-facing experience in startups or devtools, background as ML engineer or solutions architect
Technologies
AWS, Lambda, CoreWeave, Runpod, NCCL, Kubernetes containers
Responsibilities
Run standardized and custom benchmarks to prove value to customers, diagnose performance issues in GPU workloads, maintain benchmarking scripts and environments, generate clear technical reports and handoffs, optimize cluster configurations based on trial results
Seniority
Mid-level, hands-on IC
