4 days ago
Bengaluru, IndiaStaff+
Responsibilities
- Lead validation and quality ownership of AI/ML compute stacks on Ubuntu and Yocto.
- Define validation strategy, test architecture, and coverage for functional, performance, stress, regression, and scalability testing.
- Own defect triage, root cause analysis, and closure throughout the defect lifecycle.
- Validate end-to-end AI pipelines, including model training, conversion, optimization, kernel execution, memory transfers, and inference accuracy.
- Define and execute benchmarking and profiling strategies for training and inference workloads.
- Analyze compute, memory, and latency bottlenecks and drive system-level and model-level optimizations.
- Validate AI frameworks and runtimes including PyTorch, TensorFlow, and ONNX Runtime.
- Execute and optimize workloads on ROCm/HIP, CUDA, OpenCL, and heterogeneous accelerators.
- Design and own Python-based automation frameworks for validation, benchmarking, and reporting.
- Improve validation scalability, efficiency, and performance coverage.
- Collaborate with compiler, runtime, driver, and hardware teams.
- Provide technical leadership and mentorship to senior and junior engineers.
- Communicate validation status, performance metrics, and quality risks to stakeholders.
Requirements
- 8–12 years of experience in AI/ML software validation or performance engineering.
- Strong Python scripting and test automation expertise.
- Strong machine learning fundamentals, including deep learning and LLMs.
- Hands-on experience with ROCm validation, performance profiling, and optimization.
- Experience with HIP, CUDA, OpenCL, and TensorFlow/PyTorch integrations.
- Proven experience validating end-to-end AI pipelines.
- Strong Linux expertise, including Ubuntu and Yocto.
- Ability to lead initiatives independently with strong ownership.
- Strong analytical, problem-solving, written communication, verbal communication, and cross-functional collaboration skills.
- Bachelor’s or master’s degree in AI/ML, Robotics, Electronics, Computer Science, or a related field.
Categories
About AMD
AMD designs and sells CPUs, GPUs, and adaptive/embedded computing products for PCs, data centers, gaming, and edge devices. Its portfolio includes Ryzen and EPYC processors, Radeon and Instinct graphics, and adaptive SoCs from its Xilinx acquisition, sold to OEMs, cloud providers, and device makers. Founded in 1969 and headquartered in Santa Clara, it is a public company on NASDAQ and supplies semi-custom chips for major game consoles.