Job Location: Hyderabad/Secunderabad
You will contribute to the core team that validate the tests for AMD GPU based compute software stack. You will be responsible for maintaining the ROCm stack quality by running those test suites (automated, manual) and suggest enhancements that ensure enterprise quality for AMD s Software Compute stack.
You will work closely with other software and hardware engineers and architects This is an exciting opportunity to work on the cutting edge of GPU Compute technologies. Candidates with a solid foundation in computer science, research or project experience in GPU rendering, Machine Learning and performance are very welcome.
Candidates with strong foundation in the QA Processes Terminologies, Linux Internals, Machine Learning and aspiring to go above and beyond will be successful in this role.
- Responsible for AMD s new GPU/System bring up, ROCm SW stack testing, etc.
- Responsible for quality and performance timeliness of result for a portion of project/process
- Contribute to Improving overall process, quality of products
- Be involved in the automation of manual test cases and work closely with automation infrastructure
- Executing white box, black box, and regression tests for existing ROCm features
- Responsible for quality and timeliness of results for a portion of the project/process.
- Make more complex technical decisions independently.
- Implement checks and balances independently to minimize the impact of mistakes.
- Good understanding of test and development lifecycle, QA process terminology
- Strong hands-on knowledge of Linux Internals, Device drivers, Graphics, GPU and CPU pipelines, parallelism, cache, and other performance factors
- Good understanding of PC hardware, SoC, Chipsets, Graphics cards, BIOS VBIOS
- Define, Develop, Execute, Debug Software Stack level problems from functional, performance, load tests, and endurance testing.
- Hands-on system-level debugging and triage skills, issue isolation with various components of Linux (Compiler, Kernel, etc.)
- C++ system-level programming, data structures, and algorithms is an advantage
- Establishing and sharing best practices, designing, and executing a robust test strategy
- Strong analysis, problem-solving interpersonal skills
- Proficiency in at least one programming language preferably Python
- Understanding of Machine Learning, HPC apps, Computer Vision, parallel programming, OpenCL, ROCm, CUDA, and OpenACC is a plus
- Good verbal written communication skill is a must.
- Good attitude, result-driven ability to deliver on next-gen technology
- Flexible to work on a shift basis depending on the business need