דרושים » הנדסה » Senior AI Networking System Architect

we are building state-of-the-art accelerated computing platforms that know no boundaries. Our technology is crucial for global innovators, scientists, researchers, and engineersempowering them to transform their boldest concepts into tangible outcomes. Our next-generation Infiniband, NVLink, and Ethernet systems will continue to be at the forefront of connecting and powering the world's most advanced AI clusters.
We seek a highly motivated and experienced Software Architect specializing in Ethernet Switch ASICs to join our team of experts and help shape the future of high-performance ML/AI computing. You will have the opportunity to work on some of the most pioneering technologies and help drive the innovation of our next-generation networks. You will play a key role in defining switching software stacks and Linux kernel networking, and help address new business opportunities in exciting areas. Our Architects also represent our company in open-source projects, technical conferences, and standard development organizations.
What you'll be doing:
Explore networking technologies, features and protocols, hardware/software capabilities, open-source software and drivers for our Ethernet Switch ASICs and Networking platforms.
Be familiar with the Ethernet Switch ASIC hardware and software stacks, as well as with the Ethernet Switch platforms design and characteristics.
Define robust architectures and technical requirements for embedded software, meeting AI/ML workloads' needs and highly performing network operations.
Lead the work with R&D and Validation teams, providing technical guidelines and close support and thorough reviews for detailed designs and test plans.
Collaboration with architects across various fields, including Chip Design, Firmware, Hardware Platforms, and System teams.
Close work with product marketing, program managers, and account managers to ensure the successful execution of projects.
Support engagements with key customers, issue patents, publish white papers and blogs, and be proactive in technical forums and industry working groups.
Promote innovation through the design and implementation of Proof-of-Concept (PoC).

We seek a highly motivated and experienced System Architect specializing in Data-Center, AI Fabric, and Ethernet Networking to join our team of experts and help shape the future of high-performance ML/AI computing. You will have the opportunity to work on some of the most pioneering technologies and help drive the innovation of our next-generation networks. You will play a key role in defining end-to-end solutions, networking protocols and features, interworking with orchestration systems, and help address new business opportunities in exciting areas. Our Architects also represent us in open-source projects, technical conferences, and standard development organizations.

What you'll be doing:

Explore new technologies and end-to-end solutions for our Ethernet Networking Platforms.

Be familiar with data-center and AI fabric network topologies, AI/ML clusters operation and network usage, as well as with the Ethernet Switch platforms' design and characteristics.

Define robust architectures and technical requirements for network operating systems and end-to-end solution offering for AI/ML workloads' needs and highly performing network operations.

Lead the work with R&D and Validation teams, providing technical guidelines and close support and thorough reviews for detailed designs and test plans.

Collaboration with architects across various fields, including Chip Design, Firmware, Hardware Platforms, and System teams.

Close work with product marketing, program managers, and account managers to ensure the successful execution of projects.

Support engagements with key customers, issue patents, publish white papers and blogs, and be proactive in technical forums and industry working groups.

Promote innovation through the design and implementation of Proof-of-Concept (PoC).

We seek a highly motivated Network Performance Exploration Engineer to join our team of experts and help shape the foundational infrastructure for the AI revolution. Our next-generation networking systems are at the forefront of connecting and powering the world's most advanced AI clusters. As a key member of our architecture team, you will be responsible for exploring and identifying critical network optimization opportunities across our entire hardware and software stack, analyzing how system-level changes impact application-level performance.
What Youll Be Doing:
Explore and validate end-to-end application performance, defining comprehensive test plans and critical metrics to identify optimization opportunities in both hardware and software.
Establish and maintain a comprehensive database of benchmark results, tracking performance across releases to drive data-informed decisions.
Conduct deep-dive analysis into communication libraries (like NCCL), system software, and hardware configurations to investigate performance characteristics, validate architectural theories, and identify bottlenecks.
Provide critical performance data to correlate and enhance simulation tools, ensuring our models accurately predict real-world hardware behavior.
Analyze application-level traffic patterns (e.g., LLMs) on our advanced networking fabrics to identify hardware and software optimization opportunities and tune system parameters.
Lead Proof-of-Concept (POC) projects to prototype and evaluate potential hardware and software optimizations and their impact on application performance.

We are seeking a highly motivated SoC Architect to join our team and define the next generation of our companys high-performance networking SoCs. Our Ethernet and NVL switch silicon powers the world's most advanced AI compute clusters - from hyperscale GPU systems used to train and inference massive foundation models, to the AI factories shaping the future of computing.
As an SoC Architect at our company, you will drive end-to-end SoC definition, connecting system-level requirements with chip-level implementation across multiple domains. You will work closely with cross-functional teams to craft scalable, power-efficient, and feature-rich SoCs that enable the next leap in networking and AI infrastructure.
What You'll Be Doing:
Lead SoC architecture across multiple teams and disciplines - including firmware, security, debug, power management, and peripheral/IP owners - ensuring holistic architectural alignment and system coherence.
Ensure next-generation architectures meet the requirements and constraints of all stakeholder teams, and drive clear specification and communication of those requirements.
Architect and analyze multi-chip solutions, including die-to-die connectivity, chip partitioning, package/board constraints, system requirements, chip fabric, PCIe subsystem and how SoC subsystems must support them.
Define top-level SoC structure: subsystem partitioning, interconnect, memory subsystem, coherency, clocking, power architecture, and system integration.
Define system flows: power up sequences, boot sequences, software update.
Own the SoC architecture specification and guide it throughout the entire product lifecycle - concept, modeling, implementation, and silicon bring-up.
Perform trade-off analyses across performance, area, power, and feature complexity to drive architectural decisions.
Collaborate deeply with chip architects, logic design, verification, physical design, firmware, and system software to ensure seamless integration of all SoC components.
Contribute to innovation and long-term architectural direction, including patent development.

We seek a highly motivated and experienced Software Architect specializing in Ethernet Switch ASICs to join our team of experts and help shape the future of high-performance ML/AI computing. You will have the opportunity to work on some of the most pioneering technologies and help drive the innovation of our next-generation networks. You will play a key role in defining switching software stacks and Linux kernel networking, and help address new business opportunities in exciting areas. Our Architects also represent us in open-source projects, technical conferences, and standard development organizations.

What you'll be doing:

Explore networking technologies, features and protocols, hardware/software capabilities, open-source software and drivers for our Ethernet Switch ASICs and Networking platforms.

Be familiar with the Ethernet Switch ASIC hardware and software stacks, as well as with the Ethernet Switch platforms design and characteristics.

Define robust architectures and technical requirements for embedded software, meeting AI/ML workloads' needs and highly performing network operations.

Lead the work with R&D and Validation teams, providing technical guidelines and close support and thorough reviews for detailed designs and test plans.

Collaboration with architects across various fields, including Chip Design, Firmware, Hardware Platforms, and System teams.

Close work with product marketing, program managers, and account managers to ensure the successful execution of projects.

Support engagements with key customers, issue patents, publish white papers and blogs, and be proactive in technical forums and industry working groups.

Promote innovation through the design and implementation of Proof-of-Concept (PoC).

We are searching for a strong technical leader to own the backbone of our Networking Research capabilities. We are looking for an Engineering Manager to lead the development of our high-fidelity Network Simulation platform and the extensive on-premise infrastructure that powers it.

In this role, you will lead a team of performance simulation software engineers and DevOps/Infrastructure specialists. You will own the "Simulation-as-a-Service" product-a critical platform used by internal researchers to model next-generation data center architectures. Your mission is to ensure our simulations are accurate, performant, and accessible, while managing the large-scale compute clusters required to run them.

What you'll be doing:

Team Leadership: Manage and mentor a team of C++ software engineers and DevOps infrastructure engineers, fostering a culture of performance, reliability, and code quality.

Product Ownership (Sim-as-a-Service): Treat the internal simulation platform as a product. Work with research partners to define the roadmap, prioritize features, and ensure high availability for users.

High-Performance Simulation: Be responsible for the architecture and optimization of complex network simulation engines (C++ based), ensuring they can scale to model extensive data center topologies with high fidelity.

Infrastructure Management: Own the lifecycle of our on-premise compute clusters and servers. Drive decisions on hardware upgrades, prioritisation, and managing system resources.

DevOps & Automation: Lead the strategy for CI/CD pipelines, automated testing, and containerized deployments to ensure rapid iteration and stability of the simulation platform.

multi-functional Collaboration: Partner with the AI Agents team to expose simulation APIs, enabling agents to run experiments and gather data autonomously.

We are looking for an excellent System Eng. First line manager to join our group in Yokneam.

As the team manager, you will be leading a development team responsible for the System bring up of the Next-generation networking products. The team focus is on Firmware validation tests for advanced cutting-edge NVIDIA networking and AI platforms and silicon. We drive the data growth of the worlds biggest companies, Working with talented engineers around the globe, the work environment is dynamic, meaningful, and fast-paced.


What you will be doing:

Lead a team of engineers and provide technical guidance and career mentorship to the team of highly skilled engineers. Empower the team members to excel and increase team productivity.

Define and implement new product integration and validation in the core of our HCA and DPU products.

Drive and facilitate the planning, scheduling, and execution of the project and activities of the team.

Collaborate with architecture, product and different software design teams as part of the software development lifecycle.

Work in pre and post-silicon activities of our next-generation networking products.

Gain a deep understanding of networking technology, system debugging, as well as the HW/FW/SW relationship.

We are seeking a passionate and innovative Senior Software Engineer with expertise in enterprise and data center networking to join our Cumulus Linux team. Cumulus Linux is a leading open-networking operating system and a cornerstone of the AI Factory - the next-generation data center designed to power the training, fine-tuning, and deployment of AI models at scale. As part of the team, you will design and implement core features of Cumulus Linux that enable the worlds most advanced data centers. You will work closely with cross-functional architecture and design teams, shaping the future of our networking technologies while gaining hands-on experience across our hardware and software ecosystem - from advanced networking ASICs to large-scale distributed systems.

What you'll be doing:

Design, develop, integrate, and test data forwarding and routing features in our Cumulus Linux.

Enable our Cumulus Linux on next-generation ASICs.

Work collaboratively with team members, product managers, architects, QA, and other engineering teams to deliver high-quality solutions.

Innovate and rapidly develop proof-of-concept (POC) prototypes that can evolve into fully developed products or solutions.

Engage closely with customers to understand their challenges, use cases, and deployment strategies, and devise innovative solutions.

We are looking for an AI Test Architect joining E2E Verification group to profile Innovative large scale Distributed training on our AI End-to-End solutions in a large scale supercomputing clusters. Provide insights on at-scale system design and tuning mechanisms for large-scale compute runs. You will work with the latest Accelerated Computing and Deep Learning software and hardware platforms, with researchers, developers, and customers to craft improved workflows and develop new, leading differentiated solutions. You will interact with HPC, OS, Switch, HCA, CPU and GPU compute, and systems specialist to architect, develop and bring up large scale performance platforms.

What youll be doing:

Profiling, benchmarking, and analyzing deep learning models to identify areas for optimization and improvement in terms of performance, efficiency, and accuracy, with a strong emphasis on networking aspects.

Collaborating closely with data scientists, researchers, development, automation teams to design and implement scalable training pipelines and frameworks that demonstrate large scale high -performance networking capabilities.

Staying up-to-date with the latest advancements in deep learning algorithms, architectures, our GPU technologies, and high-performance networking solutions.

Optimizing deep learning models for performance, memory usage, and power efficiency while maximizing high-performance networking features on our supercomputers.

Providing insights and recommendations based on the analysis of large-scale training results, specifically focusing on networking bottlenecks and optimizations, to improve model outcomes and achieve business objectives.

Collaborating with hardware engineers to guide the development and integration of efficient networking solutions for deep learning, including exploring network architecture optimizations and bringing to bear technologies such as RDMA or InfiniBand.

We are looking for a 100% hands-on Storage Services Software engineer to join the block storage group. You will be a member of a team that builds the next generation block storage capabilities. You will work closely with a variety of teams and architects including the networking team, and external customers. You will take part in defining the software architecture and implementation of the most advanced storage services! Services that will need to meet extreme performance and scalability demands! We have crafted a team of extraordinary people stretching around the globe, whose mission is to push the frontiers of what is possible today and define the platform of tomorrow.

We work, think and learn as a team. We thrive in a deeply strong environment, and we're passionate about a culture that demands innovation and the highest standards. The rewards are sweet and include collaborating with some of the smartest people in the industry, an aggressive compensation plan that rewards top performers, and the opportunity to work on products that transform the way people work and play.

What youll be doing:

100% hands-on coding role in C language, kernel and userspace.

Research, design, implement and test, new and existing, networking features for distributed storage services and features of our block storage solution, in both Host and DPU environments.

Acquire understanding of the algorithms, the technicalities and the interaction with other components across our block storage ecosystem.

Analyze and solve challenging bugs and customer cases in large scale production systems, identifying issues in our or inbox kernel modules and often in other components. Drive new solutions based on any issues that arise.