OpenAI21.04.2026
3P Silicon Architect
Зарплата не указана
Полная занятостьУдалёнка
Обязанности
- 01Engage deeply with silicon vendors (e.g NVIDIA & AMD) on GPU and accelerator architecture tradeoffs
- 02Analyze and interpret performance, power, and efficiency characteristics of next-generation hardware
- 03Translate vendor specifications into expected real-world performance for AI workloads
- 04Evaluate architectural aspects including compute throughput and utilization, memory systems (HBM, cache hierarchies, bandwidth constraints), data types and precision tradeoffs (FP16, BF16, FP8, etc.), interconnect and scaling behavior
- 05Run benchmarks and profiling to validate hardware performance against workload requirements
- 06Lead early bring-up and evaluation of engineering sample (ES) silicon
- 07Partner with performance modeling and system architecture teams to align measured vs. modeled behavior
- 08Provide actionable feedback to vendors to influence future silicon design and roadmap decisions
Требования
- 01Deep expertise in GPU or accelerator architecture, including performance and power tradeoffs
- 02Understanding of AI workload behavior and how it interacts with hardware design choices
- 03Comfortable engaging directly with silicon vendors at a technical architecture level
- 04Hands-on experience with benchmarking, profiling, and performance analysis
- 05Ability to translate low-level hardware details into system-level and workload-level impact
- 06Equally comfortable in theory (architecture) and practice (measurement/validation)
- 07Thrive in environments where you bridge internal teams and external partners
Условия
- 01Role based in San Francisco, CA
- 02Hybrid work model of 3 days in the office per week
- 03Relocation assistance offered