דרושים » הנדסה » Firmware Engineer - Ethernet Switching

We are looking for an excellent Firmware Design Engineer for NVIDIA FW PHY Group. The person will closely work with NVIDIA FW development, architecture, chip design teams and gain deep understanding of NVIDIA's Networking products and technologies. We have some of the most forward-thinking and hardworking people in the world working for us. Are you a creative and autonomous engineer who loves a challenge? Are you ready to become the engineer you always wanted to be? Come and be part of the best chip design team in the industry!

What youll be doing:

Working on the most Ground breaking technology for building AI infrastructure.

Design and develop PHY-layer firmware for our latest networking devices, improving performance and reliability in our next-generation products.

Enabling new SerDes and physical linkup flows.

Work closely with the architecture, HW, and SW design teams.

Define implement and maintain FW algorithm to control the Silicon.

Develop and test FW on emulation & simulation environments during the Pre-silicon phase.

Debug and screen HW/FW/SW issues.

Take an active part in silicon bring-up and SW development phases.

Lead data-driven discussions about the product functionality and areas for improvement.

We are looking for an excellent Software Manager to join the Switch SDK Group and lead a team of powerful software engineers. You will join the SDK group and take our product to next level, working closely with various other design and architecture teams and gain a deep understanding of our products and technologies. We have been redefining computer graphics, PC gaming, and accelerated computing for more than 25 years. Its a unique legacy of innovation thats fueled by great technology-and amazing people.

What you'll be doing:

Leading and managing a dynamic team of engineers, ensuring smooth and efficient project execution.

Developing and implementing our Ethernet SDK with a focus on high-performance and reliability.

Collaborating with teams from other subject areas to identify technical requirements and successfully implement innovative solutions.

Following established guidelines and standards to ensure the delivery of high-quality products.

Continuously striving for excellence, improving team performance, and driving innovation.

We are seeking a technical leader to define, craft, implement, and guide firmware architecture for reliability, availability, serviceability, and power management across next-generation Networking products and platforms. You will take a strong hands-on role, working with hardware, firmware, software, validation, customer engineering, and external partners to build robust, diagnosable, power-efficient systems for large-scale deployments.

What you'll be doing:

Define platform-level firmware architecture for RAS and power management across SoCs, accelerators, DPUs, servers, embedded systems, and data center platforms.

Own error detection, classification, containment, recovery, escalation, and reporting architecture.

Define firmware architecture for power sequencing, power states, reset flows, thermal and power fault handling, idle management, and recovery from power-related failures.

Create firmware specifications for hardware error handling, health monitoring, crash capture, telemetry, diagnostics, debug data, and field serviceability.

Define interfaces and contracts between firmware, hardware, operating systems, BMCs, management controllers, platform software, and cloud/service infrastructure.

Drive architecture reviews, tradeoff discussions, failure-mode analysis, validation strategy, and long-term RAS and power management roadmap planning.

Establish standards for error logs, event schemas, telemetry flows, recovery policies, service diagnostics, and production debug infrastructure.

Guide engineering teams through implementation, validation, silicon bring-up, platform integration, and production deployment of RAS and power management features.

Analyze customer and field failures, identify architectural gaps, and feed lessons learned into future platform designs.

We are actively seeking an outstanding Software Director to lead our Spectrum Ethernet Switch/SmartSwitch SONiC Group. As part of this team, candidates will engage with SONiC, a collaborative open-source initiative spearheaded by CSPS and numerous vendors, which enables a single network operating system to operate seamlessly across diverse ASICs and platforms. Notably, we have been a major contributor to SONiC since its inception, and our technology is already powering Ethernet Switches, DPUs, and soon BMCs, making SONiC an integral component in RDMA and AI datacenter environments.

What you'll be doing:

As Software Director, candidates will oversee the design, development, and optimization of networking protocols for switching, routing, analytics, telemetry, and more.

They will manage global teams composed of both junior engineers seeking mentorship and seasoned embedded software experts who provide leadership within and beyond the group.

Collaboration will be key, as the role involves working closely with various design and verification teams, architects, product marketing professionals, and both internal and external customers to ensure end-to-end project success.

We are looking for a talent Software Engineer to join our Ethernet Switch SONiC Network OS. We have amazing GPUs that power AI applications, but they also require a high-performance network to support them. As a team member, you will have the opportunity to create innovative software that optimizes AI networks for the best performance possible. In this position you will take part in SONiC large worldwide community, contributing new features, bugs fixes and have our Switch products running with SONiC NOS in production in different clusters over the world.


What you'll be doing:

Design and implement features as part of the SONiC release train on top of our Switch products.

Be part of our SONiC R&D team, contribute code to SONiC worldwide community.

Work in a Continuous Deployment environment of fast development/deployment cycles.

Work with experienced teams which are well known in the SONiC community.

We are transforming the world of networking for massively scaled AI factories through Spectrum-X: Our Ethernet Networking solution. We need automation engineers with strong coding skills to join our Spectrum-X team and create the products that will drive the next phase of AI growth. Aa a Software Engineer you will ensure that the solution's software features are developed, tested and delivered to meet the high standards of our customers. Do you want to help create the most exciting solutions in the world of networking today? If so, read on.

What you'll be doing:

Participating in an international team of software engineers working on products for testing our ethernet networking products.

Designing and implementing robust, maintainable, and efficient automation test suites for end-to-end testing of AI ethernet networks.

Engaging directly with our customers to ensure we are aligned on their networking requirements and solve their problems.

Debugging and diagnosing complex networking problems.

We have been transforming computer graphics, PC gaming, and accelerated computing for more than 25 years. Its a unique legacy of innovation thats fueled by great technology-and amazing people. We are now seeking a highly motivated Infrastructure, Tools & AI Engineering Manager to join our Ethernet Switching group, working on SONiC Network OS. In this role, you will own and drive the engineering infrastructure that powers the full product development lifecycle - from development environments and CI pipelines through regression, code coverage, and test efficiency. You will apply cutting-edge AI and LLM capabilities to transform how we analyze failures, generate test coverage, and accelerate product quality.

What youll be doing:

Lead and mentor a team of infrastructure and tooling engineers; set technical direction, define priorities, and grow team capabilities.

Design, build, and maintain scalable infrastructure for development, integration, and test environments supporting SONiC OS.

Architect and deliver LLM-based tools for intelligent regression analysis - failure classification, root cause clustering, anomaly detection, and test flakiness prediction.

Lead efforts to reduce regression runtime through parallelization, smart test selection, and dependency-aware scheduling.

Develop deep technical knowledge of SONiC Network OS internals, including its subsystem architecture, SAI/ASIC abstraction layer, and management plane.

We're looking for a Senior Data Scientist to join the AI cybersecurity team in the Security and Networking Architecture group. As a Senior Data Scientist youll have the opportunity to take an active part in the research and development of our world-class networking and data center security products. This role involves creative problem solving alongside engineering teams, and is key for the continued success of AI networking security.

What youll be doing:

Developing agentic AI systems for security, combining generative models, RAG, and tool-augmented reasoning to automate threat analysis and response workflows.

Optimizing and fine-tuning models for performance, scalability, and resource utilization, considering factors such as latency, efficiency, and cost.

Developing, implementing and improving models and algorithms across media types, whether time series, images, text, audio or video.

Leveraging data pipelines to efficiently process and transform large volumes of data for training and inference purposes.

Applying alignment techniques and parameter efficient fine-tuning to improve model performance.

Measuring and benchmarking model and application performance to drive improvements.

Driving the gathering, building, and annotation of domain specific datasets for benchmarking and training.

Collaborating closely with software and hardware engineers on new features and improvements. Participate in developing and reviewing code, design documents, use case reviews, and test plan reviews.

We are seeking a highly skilled and motivated Electrical Validation (EV) Team and System Testing / ATE Team Leader to join our team. This position is crucial in supporting the design, development, and implementation of Automated Test Equipment (ATE) and production test systems.
The Electrical Validation team Lead manages the electrical validation function across our company hardware platforms. This role owns the validation strategy, methodology, lab infrastructure, and execution across all high-speed and control interfaces. The manager ensures robust electrical performance from early prototypes through production release and drives cross-functional alignment between design, SI, firmware, and manufacturing.
The role involves close collaboration with the HW R&D team, Quality, DevOps, and Contract Manufacturing (CM) teams to ensure the delivery of high-quality, reliable products.
This group is part of the HW R&D group.
Key Responsibilities
Define the electrical validation strategy for our company hardware platforms.
Own validation methodology for: High-speed Ethernet (100M-1600G), PCIe Gen1 to Gen5+, SerDes architectures (NRZ/PAM4), Control and management buses (I2C, SPI, RS-232, MDIO, etc.)
Establish structured validation plans aligned with hardware release milestones.
Build and manage a high-performance validation team.
Define lab architecture, including: Equipment selection (oscilloscopes, BERTs, analyzers), Compliance platforms, Automation frameworks, Signal integrity validation environments
Drive early engagement with board design and SI teams to ensure design-for-validation.
Oversee: Compliance (IEEE, PCI-SIG, OIF), Interoperability testing, Stress and margin testing
Lead root cause analysis of electrical failures and systemic issues.
Support NPI, manufacturing bring-up, and yield improvement.
Develop automation and scalable validation methodologies.
Define validation documentation standards and sign-off criteria.
Collaborate with system architecture and software teams to ensure HW-SW integration robustness.
Manage external labs and certification processes where required.
Drive continuous improvement of validation coverage and efficiency.
Lead the full ATE development lifecycle from requirements definition to execution in production, including GUI design and Python scripting.
Develop and maintain boundary scan applications using JTAG Technologies.
Define and maintain test fixtures, including JIGs/Bed-of-Nails, etc., in collaboration with mechanical vendors.
Implement full test traceability systems for production yield and stability monitoring.
Collaborate with R&D and Quality teams to drive product quality and reliability improvements.
Provide onsite support at CM sites, including station setup, installation, training, maintenance, and debugging.
Perform in-depth failure analysis and troubleshooting at the system and component level.
Utilize and maintain a range of test equipment, including:
Work with various communication protocols: TCP/IP, Telnet, SSH, HTTP, SNMP, SFTP, SCP, FTP, RS232, GPIB, I2C, and NI-VISA.
Support testing of embedded systems running on Linux platforms.

We are looking for a highly skilled Advanced Development Engineer to join the Software Architecture Team. In this hands-on role, you will shape the future of large‑scale data centers through advanced simulation, high‑scale telemetry, and next‑generation infrastructure solutions. You will work at the frontier of technology - exploring, prototyping, and proving new concepts - and turn them into scalable, production‑ready foundations. Your work will span large‑scale telemetry pipelines, data integrity at extreme scale, and advanced simulation frameworks used to model, validate, and optimize complex data‑center environments.

As part of the Architecture team, you will directly influence cross‑company platforms and long‑term technology direction, while actively contributing code, frameworks, and ideas. You will also have opportunities to participate in and contribute to open‑source projects and communities.

What you'll be doing:

Discover, evaluate, and prototype emerging technologies with a strong focus on simulation, scale, and system behavior modeling.

Design, implement, and evolve high‑scale software systems integrated across the full Data Center life‑cycle.

Build advanced simulation solutions to model data‑center behavior, telemetry flows, failure scenarios, and system performance at scale.

Define and expand large‑scale telemetry and observability pipelines, ensuring accuracy, consistency, and traceability of data.

Incorporate new and diverse data sources to continuously extend the capabilities of a centralized, petabyte‑scale Data Lake.

Collaborate closely with engineering, architecture, and research teams across us to translate business and technical requirements into robust, scalable solutions.

Work side‑by‑side with architects and data scientists to design, validate, and evolve data and simulation architectures.

Contribute to defining the architecture of next‑generation monitoring, analytics, and simulation platforms for hyperscale data centers.

Extend existing platforms and actively contribute code, designs, and leadership to Open Source projects and communities.