Own verification of complex ASIC and FPGA designs, building UVM environments, driving coverage-based plans to closure, and partnering with RTL engineers to deliver reliable silicon.
Design and implement system software that connects AI frameworks with low-level infrastructure, enabling large-scale models to run efficiently across GPU clusters through performance analysis and optimization.
Build automated testing frameworks and stress-testing suites to validate the reliability and performance of AI infrastructure across distributed training, inference, GPU kernels, and system boundaries.
Own a strategic customerβs production deployment of AI infrastructure software, solving cluster integration and operational challenges while turning field insights into product features and supporting future customer deployments.
Leads board and system design for server and data-center compute platforms, from architecture and ODM coordination through high-speed interface validation, board bring-up, and manufacturing support.
Architect and deliver advanced multi-die packages for high-performance AI accelerators, owning package architecture, substrate design, manufacturability, and vendor engagement from specification through bring-up and qualification.
Own DFT verification for ASIC logic, building UVM environments and coverage-driven plans, validating scan, MBIST, and ATPG behavior, and partnering with design and manufacturing teams through verification closure and silicon bring-up.
Leads SerDes physical-layer implementation, equalization tuning, and post-silicon validation for ultra-high-speed links, driving stable performance through lab characterization and cross-functional debugging.
Own complex ASIC and SoC physical implementation from floorplanning through signoff, drive timing and power-integrity closure, improve design methodologies, and provide technical leadership across the physical design team.
Build automation frameworks and stress-testing suites to validate the reliability and performance of AI infrastructure across distributed systems, GPU kernels, and AI frameworks.
Build automation frameworks and stress-testing suites to validate the reliability and performance of AI infrastructure across distributed systems, GPU kernels, and AI training and inference workloads.
Design and optimize system software that connects AI frameworks with low-level infrastructure, enabling large-scale models to run efficiently across GPU clusters through distributed execution and performance analysis.
Page 1 Β· 12 results
