Staff GPU Inference SDET (AI)

Location: Hybrid in Sunnyvale, California, or Toronto, Canada

Company

hirify.global builds large-scale AI computing hardware and infrastructure for high-speed model training and inference.

What you will do

• Design and scale automated release qualification systems, regression gates, and test pipelines for the GPU inference stack.
• Validate multi-node GPU cluster bring-up, model-serving workers, serving engines, container runtimes, drivers, and firmware.
• Benchmark distributed LLM serving workloads, including prefill and decode performance, continuous batching, prefix caching, KV-cache efficiency, and parallelism.
• Build workload replay and performance validation tools tracking TTFT, inter-token latency, throughput, tail latency, and capacity efficiency.
• Ensure numerical correctness, precision stability, determinism, and output quality across software and hardware changes.
• Develop fault-injection and chaos-testing suites for node failures, network degradation, memory leaks, driver or firmware mismatches, and recovery paths.

Requirements

• 8+ years of software engineering experience as an SDET, infrastructure quality lead, or systems test engineer.
• Hands-on experience provisioning and validating multi-node NVIDIA or AMD GPU clusters in public cloud or enterprise data center environments.
• Deep understanding of LLM serving engines, distributed runtimes, prefill and decode disaggregation, KV-cache management, and dynamic batching.
• Expert-level Python skills with experience building test automation frameworks, diagnostic tools, and CI/CD integrations.
• Strong proficiency with Kubernetes, Slurm, or Ray and high-performance interconnects such as InfiniBand, RoCE, or NCCL.
• Experience with root-cause analysis across software and hardware boundaries, stress testing, and distributed-system failure simulation.

Nice to have

• Experience with AMD ROCm/HIP or NVIDIA software stacks.
• Experience building workload replay tools, ML evaluation pipelines, or MLPerf Inference benchmark suites.
• Familiarity with PyTorch Profiler, NVTX, ROCm profilers, or C++.

Culture & Benefits

• Opportunity to build AI hardware and infrastructure beyond conventional GPU constraints.
• Access to cutting-edge AI research, open-source work, and high-performance AI supercomputing systems.
• Startup vitality combined with job stability.
• Non-corporate work culture focused on individual perspectives, learning, growth, and inclusion.