Member of Technical Staff (AI Inference)

Location: San Francisco, CA, United States; on-site

Salary: $150K–$390K annually, plus equity

Company

hirify.global is building a multi-silicon neocloud for fast, efficient AI inference by combining large-scale compute infrastructure with an execution platform that maps AI workload stages to suitable hardware.

What you will do

• Establish performance baselines for production inference workloads across established and emerging accelerator architectures.
• Analyze bottlenecks across compute, memory, caching, kernel launch, synchronization, host-device interaction, communication, and runtime scheduling.
• Use profiling, hardware counters, controlled experiments, and performance models to identify high-leverage optimizations.
• Improve execution through launch reduction, graph capture, stream and event coordination, compute-communication overlap, memory reuse, batching, and scheduling.
• Build automated benchmarks and regression detection across models, tensor shapes, data types, software releases, and hardware targets.
• Translate performance findings into production improvements and develop methodology for evaluating and bringing up new accelerators.

Requirements

• Strong software engineering fundamentals and experience working on performance-critical systems.
• Experience profiling GPU or accelerator workloads and turning measurements into production improvements.
• Strong understanding of GPU execution, memory hierarchies, asynchronous execution, synchronization, and performance tradeoffs.
• Ability to design controlled experiments, distinguish symptoms from root causes, and communicate performance findings precisely.
• Bachelor's degree in a relevant field, or an equivalent combination of education, training, and professional experience.

Nice to have

• Experience with Nsight Systems, Nsight Compute, rocprof, Omniperf, VTune, Perfetto, or hardware performance counters.
• Experience with CUDA, HIP, Triton, or another accelerator programming model, including prototyping low-level optimizations.
• Familiarity with roofline analysis, queueing behavior, occupancy, latency hiding, instruction throughput, and memory-bandwidth analysis.
• Experience optimizing inference runtimes, execution graphs, memory allocators, kernel dispatch, batching, or model-serving systems.
• Familiarity with collective communication, topology-aware execution, and compute-communication overlap across multiple accelerators.
• Experience building performance laboratories, benchmark suites, regression infrastructure, or hardware bring-up methodology.

Culture & Benefits

• Work on frontier AI inference, production infrastructure, emerging hardware, and new data centers.
• Access to technical problems spanning foundation labs, hyperscalers, and AI-native companies.
• Opportunity to solve hard problems, own meaningful work, and build for production.
• Equity is offered as part of compensation.