3 days ago
Bengaluru, IndiaSenior / Staff+
Responsibilities
- Design and develop custom GPU kernels for attention mechanisms, collective operations, and computation primitives on Intel accelerators and GPUs.
- Optimize AI framework scheduling, memory management, execution pipelines, throughput, latency, and resource utilization.
- Write and integrate high-performance kernels for production AI workloads.
- Identify and implement optimization opportunities across the AI framework software stack.
- Collaborate with and contribute upstream to SGLang, vLLM, PyTorch, and other open-source projects.
- Debug and optimize multilayered systems involving kernel execution, memory hierarchies, and distributed AI workloads.
Requirements
- Bachelor's degree or master's degree in Computer Science, Electronics and Communications Engineering, or a related field.
- 6 to 12 years of professional experience.
- Advanced proficiency in C++ and intermediate skills in Python and parallel programming.
- Hands-on experience writing and optimizing GPU kernels for GEMM, attention mechanisms including Flash Attention, collective operations, and sampling.
- Deep experience with SGLang, vLLM, PyTorch, or similar production-grade AI serving and training frameworks.
- Strong understanding of AI inference and training, batching, memory optimization, distributed execution, and performance tuning.
- Experience deploying and optimizing AI models and production frameworks at scale.
- Ability to debug complex systems, profile performance, and identify bottlenecks.
- Understanding of computer architecture, GPU execution models, memory hierarchies, and hardware-software co-optimization.
- Preferred experience with CUDA, CUTLASS, or Triton; compiler algorithms; kernel fusion; open-source AI framework contributions; distributed AI workloads; multi-GPU scheduling; quantization; and mixed-precision inference and training.
- Strong communication and cross-functional collaboration skills.
Benefits
- This is an experienced-hire position based onsite in Bangalore, India.
- The role is listed as Shift 1 in India.
Categories
About Intel
Intel is a public semiconductor company that designs and manufactures CPUs and other silicon for PCs, servers, networking, edge, and embedded systems, and also offers foundry services plus AI and graphics accelerators. Founded in 1968 and headquartered in Santa Clara, it sells primarily to OEMs, cloud providers, and device makers worldwide. Its portfolio includes x86 processors (Core and Xeon), Ethernet and chipset products, and the Mobileye autonomous driving platform.