Role overview
Translate measured workload limits into hardware systems research, from processors and memory to interconnects, packaging, power, thermal constraints, and test. Each project starts with a defined question, a commercial baseline, and a proof plan, and should produce evidence that supports a practical next step for the system.
Responsibilities
- Convert workloads, traces, failures, and scaling limits into quantitative hardware requirements.
- Model tradeoffs in compute, memory capacity and bandwidth, data movement, latency, interconnect, power, thermal behavior, reliability, and cost.
- Compare software improvements, commercial components, architecture changes, simulations, FPGA prototypes, and physical implementation paths.
- Define interfaces, verification plans, workloads, reference models, error budgets, resource needs, and stop conditions.
- Build or guide analytical models, simulators, RTL or FPGA experiments, and integrated software-hardware tests.
- Coordinate scoped external technical work with clear access, ownership, rights, safety, and publication terms.
Requirements
- Advanced training or equivalent experience in computer architecture, electrical engineering, or hardware systems.
- Experience in architecture analysis, performance modeling, RTL, verification, FPGA, memory, interconnects, DFT/test, or package-level design.
- Ability to translate application behavior into measurable hardware requirements.
- Ability to distinguish analytical models, simulations, prototypes, and measured device evidence.
- Understanding of verification, test, power, thermal, reliability, and economic constraints.
- Clear technical writing for software, hardware, research, partner, and business audiences.
Nice to have
- HBM, memory controllers, or interconnects; chiplets, die-to-die links, packaging, or test; FPGA, emulation, or driver integration; physical design, DFT, or silicon bring-up; or research program ownership and technical transfer.