Lead Vector Compute Architect Bolt Graphics
Core
Define data parallel microarchitecture, drive architecture tradeoff analysis, and develop system specifications for high-performance graphics compute.
Role type
Lead Vector Compute Architect (Graphics)
Builds
High-performance graphics compute systems and microarchitectures
Domain
Semiconductor / Graphics Processing Units (GPU) / Data Parallel Computing
Required skills
Data parallel microarchitecture design, Architecture tradeoff analysis, System architecture specification, Performance modeling, Memory hierarchy design, Cache coherency architecture, RTL development, Verification strategy, Silicon bring-up and debugging, Roadmap planning
Preferred skills
Workload characterization, Out-of-order execution design, NoC/interconnect design, High-speed interface design, Power/performance/area optimization
Technologies
C/C++, SystemC, RTL, PCIe, UCIe, Ethernet, DDR, LPDDR, HBM, GDDR, CHI, ACE, CXL
Responsibilities
Define data parallel microarchitecture satisfying ISA constraints; Drive architecture tradeoff analysis for performance, power, area, bandwidth, latency, and scalability; Develop and review system architecture specifications, interface definitions, and microarchitecture requirements; Lead performance modeling, workload analysis, and bottleneck identification; Define memory hierarchy, coherency architecture, and cache structures; Support silicon bring-up, debug, performance tuning, and post-silicon optimization; Contribute to long-term technology and product roadmap planning.
Seniority
Senior, hands-on IC