דרושים » חומרה » Senior AI Modeling Architect

As HW Architect Team Leader, you will combine deep technical leadership with people leadership. You will shape next-generation networking silicon while building and mentoring a strong architecture team.

What Youll Be Doing
Lead, manage, and mentor a team of HW architects, fostering technical excellence and innovation.
Drive research, evaluation, and architectural definition of next-generation SoCs - from product requirements through production.
Define next-generation Packet Processor / Datapath / Congestion Management architectures for high-performance, complex SoC Ethernet and NIC switches.
Lead system architecture and detailed micro-architecture definition across major functional blocks.
Collaborate cross-functionally with design, verification, modeling, software, and other architecture teams to ensure end-to-end system alignment.
Identify and evaluate new technologies, methodologies, and architectural approaches for future products.
Provide technical direction, make key architectural trade-offs, and ensure execution excellence.

We are a highly experienced architecture group specializing in switch processing, with deep expertise in both hardware and software architecture in the high-speed networking domain.
Our innovative packet processors power some of the most advanced data centers in the world and are designed into tier-1 vendor platforms. With state-of-the-art technology, a strong track record of industry recognition, and multiple award-winning achievements, we continuously push the boundaries of performance and scalability.
Our group is involved across the entire development lifecycle - from early research and architectural definition to silicon production - working on both research initiatives and production-grade products.


What will you be doing?
Lead research, evaluation, and architectural definition of next-generation chips - from requirements through production.
Define next-generation Packet Processor / Datapath / Congestion Management architectures for high-performance, complex SoC Ethernet Switches.
Design the system architecture and detailed micro-architecture definition across major functional blocks.
Collaborate closely with design, verification, and modeling teams to ensure architectural intent is fully realized.
Work cross-functionally with other architecture teams to shape cohesive system solutions.
Explore and evaluate new technologies and innovative approaches for future products.

Required Machine Learning Hardware Architect, Hardware, Software Co-Design, Cloud
About the job
In this role, youll work to shape the future of AI/ML hardware acceleration. You will have an opportunity to drive cutting-edge TPU (Tensor Processing Unit) technology that powers our most demanding AI/ML applications. Youll be part of a team that pushes boundaries, developing custom silicon solutions that power the future of our TPU. You'll contribute to the innovation behind products loved by millions worldwide, and leverage your design and verification expertise to verify complex digital designs, with a specific focus on TPU architecture and its integration within AI/ML-driven systems.
As a Machine Learning Hardware Architect within the Co-design team, you will serve as a technical lead bridging model architecture innovation and next-generation hardware design. Operating at the highest levels of AI research and engineering, you will define the goal and architectural roadmap for our future machine learning serving and training capabilities. You will guide the integration of ML research such as massive-scale foundation models with advanced silicon architectures to create industry-leading, high-performance, and power-efficient accelerators.
Responsibilities
Define and drive the technical roadmap and architecture for the hardware/software stack to ensure exceptional performance for ML models. Act as the technical liaison across research, software, and hardware teams, steering model architecture innovation to maximize scaling, quality, and hardware efficiency.
Architect next-generation configurable simulation frameworks and performance models, setting the organizational standard for evaluating complex microarchitectural decisions. Drive high-stakes choices regarding Power, Performance, Area (PPA) and buildability for future chip and system architectures, expertly balancing long-term technological trends with strict product delivery timelines.
Guide system-level performance analysis across highly distributed ML systems, innovating new methodologies to optimize and balance compute, memory bandwidth, and inter-chip network requirements. Their leadership will directly shape the future of high-performance AI infrastructure and hardware-software co-design.
Manage cross-functional partnerships across hardware, compiler development and ML teams.

We are looking for a Principal Engineer with deep expertise in database internals, system architecture, and hardware-aware performance optimization.
This role is responsible for defining and driving advanced database performance solutions by understanding and improving the interaction between database engines, operating systems, and modern hardware architectures.
The ideal candidate is an experienced technical leader with a strong background in database systems, performance engineering, and computer architecture. The candidate should be capable of leading complex technical initiatives, influencing architectural decisions, and developing innovative solutions for next-generation database platforms.
This is a hands-on technical leadership role requiring expertise across database kernels, query execution, transaction processing, memory systems, and low-level performance optimization.

Responsibilities
Define and drive technical direction for database performance optimization and hardware-aware database architecture.
Lead the design and implementation of advanced database optimizations focused on scalability, efficiency, and workload performance.
Solve complex performance challenges across the full system stack, including database engines, query execution, transaction processing, concurrency control, storage engines, operating systems, and hardware platforms.
Design and develop optimizations leveraging modern hardware architectures, including multi-core CPUs, large-memory systems, NUMA platforms, CXL memory, RDMA networking, and advanced storage technologies.
Improve database execution engines, caching mechanisms, memory management, storage systems, and workload scheduling.
Analyze system behavior and identify bottlenecks using profiling, tracing, hardware performance counters, and low-level performance analysis.
Develop benchmarks, workload models, and methodologies to evaluate scalability, efficiency, and architectural tradeoffs.
Collaborate with database kernel, infrastructure, and engineering teams to influence architecture decisions and deliver high-impact improvements.
Mentor senior engineers and contribute to building technical expertise across the organization.
Drive innovation through research, prototyping, technical analysis, and architectural improvements.

We are looking for an architect to work on the invention and development of new SW visible CPU technologies to improve performance of SW scenarios related to memory ordering, memory coherency, multithreading, synchronization, memory safety, caching, etc.
The minimal tasks of this role are:
1. Modeling of new memory related architectural features in the existing CPU performance simulator
2. Development of performance tests or adaptation of existing workloads to be suitable for simulation
3. Conducting performance studies for the workloads of choice either in the performance simulator or on a real chip
4. Develop analysis, conclusions and recommendations based on the above activities
The role can comprehend much more than that depending on the skills, talent and experience of the candidate creating a career path over time. For example, to invent new instructions and mechanisms to overcome significant performance bottlenecks in these areas, refinement and further development of ideas provided by others. Possible participation in development in additional domains
If you want to be part of something bigger, if you are a team player with excellent communication skills and motivation to revolutionize data-center technology, youre welcome on board!

Define the AI core architecture that will shape the next generation of AI chips, leading the global competition in AI computing power. As a key contributor to the competitiveness of AI core architecture, we drive chip architecture innovation starting from algorithm evolution, building a full-stack closed-loop capability of "algorithm-architecture-circuit-system," and creating a globally leading, independently controllable AI accelerator core to support the Ascend AI ecosystem and the implementation of large model strategies.

Responsibilities:
Modeling of HW specification of new architecture and microarchitecture. Working closely with architect and microarchitecture on modeling the specification.

The CPU Architect will take charge in defining a processor core that meets the requirement of high performance, high bandwidth, and scalable processing architecture. This architect will utilize his processor experience to deliver a world-class processor ASIC with many advanced features for Huawei products.

Our goal is to design cutting-edge CPUs for smartphones, servers, and desktops, and we need the very best talent to help us achieve it!
The CPU Micro architect will take charge in defining a processor Micro architecture features that will improve the performance and reduce the power consumption of the CPU core. This architect will use a performance simulator to explore his ideas and will analyze implementability of these features: Power, Timing, Area. This architect will utilize his processor and VLSI design experience to develop many advanced features for Huawei processors.

Be part of a team responsible for designing the next generation of mobile devices. The position includes responsibility for system analysis and HW architecture design for high-speed and low-power interfaces, networking protocols, storage processing, including acceleration of protocols reducing overall power consumption. The job requires collaboration with multiple engineering functions and teams in various geographical locations. It includes identifying system use, requirements definitions, understanding of industry specification for interfaces, operating in industry Standards committees, SW and HW interaction, performance analysis, and more.