Staff ai\/ml validation engineer
HyderabadAdvanced Micro Devices, Inc
...GPU hangs, page faults, ECC errors, memory corruption, and scheduler failures. Analyze failures using GPU traces, register dumps, crash dumps, JTAG, logs, windbg, counters and using AMD different profiler/debugger tools. Work directly with architecture, RTL, and design teams to influence fixes and mitigations. Performance [...]
Category IT & Telecommunications