Build a model enablement platform for heterogeneous AI computing across AIPUs, CPUs, GPUs, NPUs, and other accelerators. Responsibilities include model ingestion, graph partitioning, compilation, runtime execution, performance profiling, memory and scheduling optimization, large-model offloading, and verification integrated into CI. The role combines architecture ownership with hands-on C++ and Python engineering across model frontends, compilers, runtimes, and application pipelines.

Grow and manage Axelera AI’s developer community across forums, GitHub, social channels, and events. Responsibilities include answering technical questions, creating tutorials and product content, organizing webinars and meetups, building relationships with influencers and power users, advocating for community-requested product improvements, supporting open-source contributions, and tracking engagement and health metrics. The role requires technical literacy in AI hardware, SDKs, embedded systems, maker platforms, and AI-assisted content and analytics tools.

Lead and build Axelera's AI Infrastructure Systems division to deliver datacenter-class hardware from accelerator cards and OAM/UBB modules to 1U/2U racks. Own architecture, schematics, PCB/layout review, power/thermal/mechanical design, BMC/firmware, bring-up, validation, qualification, NPI, and ramp with CMs/ODMs. Align roadmaps with silicon, SDK, and product teams, engage customers and partners, set engineering processes, manage budget and vendor relationships, and mitigate technical risks through hands-on leadership.