轉職熱搜工作

* Lead specific architectural domains for SoC architecture design and product technical feasibility studies (e.g., AI, ISP, heterogeneous computing, memory, interconnect, power, safety, vehicle E/E, in-vehicle network). * Lead or support automotive SoC architecture, focusing on system performance and power based on product requirements. * Lead or support technical feasibility studies of product requirements; collaborate with domain architects and product marketing to develop competitive product design specification.

We are looking for candidates that can communicate complex engineering subjects effectively to cross functioning technical teams and upper management. Strong DFT and leadership skills will be put to good use. Successful DFT architects interact with many external teams and must confidently represent his/her organization. Key Responsibilities • Drive DFT Excellence: Define DFT architecture specifications that enhance ATE and production test environments, optimize test costs, and improve quality across future MTK ASIC product portfolios. • End-to-End DFT Leadership: Manage comprehensive DFT activities spanning architecture definition, design implementation, verification, and test deployment for new product launches • Manufacturing Integration: Serve as a key contributor within MTK’s Global Quality and Operations organization to deliver optimal manufacturing test solutions from early product conception through post-silicon validation • Design Collaboration & Quality Assurance: Partner closely with design teams to ensure accurate implementation of DFT structures and compliance with specifications • Cross-Functional Team Coordination: Lead internal DFT teams in developing and implementing robust test solutions aligned with architectural requirements • Yield Optimization Strategy: Develop comprehensive plans for diagnosability enhancement and systematic yield improvement • Location: Hsinchu, Taipei, Singapore, USA

Role and Responsibilities • Responsible for GPU cluster uArch specification, PPA (power, performance and area) optimization for industry-leading GPU hardware IP • Collaborate with Arch/Model/SW team, develop cluster level HW specification that meets feature functionality and PPA metrics • Collaborate with Arch/SW/Design team to identify and solve performance bottlenecks, power/area inefficiency issues • Guide IP design process all the way from RTL coding, verification to tape out and post-silicon debug • Proficiently use AI agent and tools to improve RTL coding, function debug and PPA analysis productivity • Execute & deliver to meet milestones/schedules. • Analyze and debug code pre-silicon and post-silicon issues. • Analyze and influence future GPU architectures. • Construct reliable & trustable relationships across teams internally & externally. • Delivering best in class GPU IP for mobile, automotive, laptop and ASIC applications

1. 具備先進製程SoC 晶片 top flow 的專業知識。 2. Advance CTS design 3. 開發先進制程的 Power Mesh 經驗。

1.從系統應用功秏分析, 與 IP, SoC 與軟體團隊合作, 推進 SoC low power 軟硬體架構的演進. 2.產品規格定義時, 分析不同架構與 IP 選項, 在系統應用功秏體驗的差異, 產出產品應用 power dash board, 提供產品規格決策的依據. 3.執行或協助功秏量測, 與power model預估的功秏做校正 4.分析PMIC/Power rail 設計, SoC power state 與 data-path power等, 並且提出SOC 設計優化方案 5.提出系統優化的方向, 達到最佳的產品電池使用續航時間與使用體驗

1. 5G/6G通訊IP開發. 2. 多模(5G/6G)解調架構開發以及RTL coding/verification/integration.

We are looking for AI hardware architect/designer to join our team and play a pivotal role in designing, developing, and optimizing architecture of the neural processing unit (NPU). As an architect/designer, you will be responsible for creating innovative hardware and software solutions that meet the performance, scalability, and efficiency requirements of our advanced NPU environment. The ideal candidate will have a strong background in computer architecture, microarchitecture, and digital design, as well as experience with industry-standard tools and methodologies. You are expected to transform novel ideas into practical proposals for future NPU products, and vet the proposals via prototyping. Extensive knowledge in compiler and operating system is a plus. International travel may be required.

1. Serdes PMA IP architecture planning 2. Serdes PMA IP RTL coding 3. Serdes PMA IP front-end and back-end integration 4. Co-work with PCS and MAC design team and DV team for IP verification 5. Co-work with Analog design team for PHY co-simulation 6. Co-work with Algorithm team for algorithm implementation and bit-true verification