AI Software Engineer - AI Frameworks
Intel, India, Bangalore
Overview
We are seeking a dynamic and passionate AI software engineer to join Intel's Data Center and AI group (DCAI). In this role, you will design and develop optimizations for high-performance AI serving and training frameworks such as SGLang, vLLM, and PyTorch. You will contribute to Intel's AI framework software stack and help enable and optimize state-of-the-art solutions for Intel's AI accelerators and next-generation GPUs. This position requires deep expertise in framework internals, scheduling, memory management, and kernel optimization for production AI workloads.
What you will do
- Design and develop custom GPU kernels for AI framework operations including attention mechanisms, collective operations, and computation primitives to optimize performance on Intel accelerators and GPUs.
- Optimize and enhance framework components including scheduling, memory management, and execution pipeline architecture to improve throughput, latency, and resource utilization.