- Bangalore, India
- On-site
- Full-time · Principal
- 8+ years
Drive technical direction and execution of AI and Generative AI workloads on GPU platforms.
Responsibilities
- Lead exploration and optimization of emerging workloads including LLMs, transformer-based models, computer vision, and other AI/ML applications.
- Collaborate across architecture, compiler technologies and frameworks such as TVM, MLIR, and IREE, software, performance, and product teams to drive solutions from early exploration through product-quality implementation.
- Provide technical leadership, conduct design reviews, and mentor engineers working across GPU AI initiatives.
- Develop and optimize GPU solutions leveraging capabilities such as matrix acceleration, mixed-precision computation, quantization, and other hardware acceleration features.
- Analyze end-to-end AI workload performance and identify bottlenecks across models, frameworks, compilers, runtimes, GPU kernels, and hardware architecture.
Requirements
- Bachelor's degree in Engineering, Information Systems, Computer Science, or related field
- Master's degree in Engineering, Information Systems, Computer Science, or related field
- PhD in Engineering, Information Systems, Computer Science, or related field