Hands-on technical capability and willingness to contribute to implementation, including development, automation, infrastructure provisioning and troubleshooting where required.
Oversee the design and delivery of global, scalable solutions to meet evolving customer needs, anticipate innovation, and guide complex transformations and strategic roadmaps.
Lead solution workshops and design reviews with customer architects, operations teams and senior executives; clearly articulate technical options, business value, risks and recommendations.
Risk Management: Identify potential project risks and develop mitigation strategies. Monitor project progress and make adjustments as necessary to address issues and ensure successful outcomes.
You'll work at the boundary of inference systems, kernels, compilers, and hardware architecture, improving performance-critical paths such as attention, GEMM, sampling, KV cache, and communication-heavy operations. Your work will help make AMD GPU support in vLLM usable, fast, benchmarked, and maintainable.
You'll work at the boundary of inference systems, kernels, compilers, and hardware architecture, improving production-relevant model serving on TPU with clear correctness, latency, and throughput benchmarks. Your work will help make TPU support in vLLM usable, fast, benchmarked, and maintainable.
Derive the tradeoffs in thermal performance of different package design elements (substrate, underfill, thermal interface material, heat spreader etc.) and chip thermal gradients from experimental test data.