Requirements

Currently pursuing a BS, MS, or PhD in Computer Science, Electrical Engineering, Computer Engineering, Electrical and Computer Engineering, or a related field
Strong coding skills with C or C++
Strong understanding of common data structures, algorithms, and design patterns
A curiosity about GPU / CPU / SOC architecture and micro-architecture
Knowledge of scripting languages such as Perl, Python or Ruby

Nice to Haves

Strong interpersonal and analytical skills
Ability to work well within a team and be productive under tight schedules
Familiarity with SystemVerilog / Verilog / VHDL
Experience optimizing rendering/parallel compute algorithms, drivers and/or compilers for one or more GPU architectures
Prior experience on hardware architectural modeling and hardware description languages
Experience with one or more GPU APIs (Metal, DX12, Vulcan, CUDA, OpenGL, OpenCL)
Knowledge of performance simulation environments
Knowledge of software design patterns

Building experience interpreting hardware specifications together with architects, micro-architects, modellers, and designers
Developing GPU workloads, automated flows, and tools to support the verification of GPU designs
Analyze the performance of existing and future-looking workloads
Propose new features and research on novel ideas to boost the performance of GPUs
Using performance and energy models to evaluate, iterate, and tune different ideas
Collaborate with a larger architecture and performance team to maintain and improve the simulation environment