Cornelis Networks delivers the world’s highest performance scale-out networking solutions for AI and HPC datacenters. Our differentiated architecture seamlessly integrates hardware, software and system level technologies to maximize the efficiency of GPU, CPU and accelerator-based compute clusters at any scale. Our solutions drive breakthroughs in AI & HPC workloads, empowering our customers to push the boundaries of innovation.

Backed by top-tier venture capital and strategic investors, we are committed to innovation, performance and scalability - solving the world’s most demanding computational challenges with our next-generation networking solutions.

We are a fast-growing, forward-thinking team of architects, engineers, and business professionals with a proven track record of building successful products and companies. As a global organization, our team spans multiple U.S. states and six countries, and we continue to expand with exceptional talent in onsite, hybrid, and fully remote roles.

About the Role
Cornelis Networks builds high-performance fabric solutions for AI and HPC. We're looking for a principal-level embedded engineer to help architect firmware across our next-generation networking silicon. A key focus of the role is the management firmware that boots, secures, and controls the on-chip compute engines that accelerate collective communication (all-reduce, broadcast, reduce-scatter), alongside broader embedded architecture work across the platform. You'll own the infrastructure layer that makes these engines trustworthy and production-ready, not the collective algorithms themselves.

This role is a mixture of hands-on architecture, firmware development, technical leadership, and mentorship, with heavy use of AI tools across design, implementation, and testing.

Location: Remote (US)

What You'll Do

Architect and implement bare-metal C firmware on a RISC-V management core that provisions, boots, and supervises arrays of on-chip acceleration engines.
Own the secure firmware-loading pipeline: fetch images from flash, coordinate hardware root-of-trust authentication, and distribute verified images into each engine's local memories through on-chip fan-out/DMA hardware.
Build per-engine bring-up, reset sequencing, and health validation driven by control/status registers, with solid
timeout and error handling and enforced security invariants.
Scale firmware distribution and bring-up across many engines and multiple dies, including runtime re-boot and in-field firmware updates.
Define the hardware/software contract with ASIC/RTL teams using a datamodel-first workflow (e.g., SystemRDL, Kaitai, YAML → generated code).
Validate firmware against functional simulators (e.g., QEMU) with automated unit and integration tests.
Set architecture standards, review designs and code, and mentor engineers.

Required Qualifications

10+ years of embedded/firmware engineering, with a track record of software architecture and technical leadership.
Expert C (C++ a plus) and working Python.
Deep experience with bare-metal firmware on constrained cores, including manually managed local memories and low level bring-up.
Experience with secure boot / image authentication and hardware root-of-trust integration.
Experience programming hardware CSRs and co-designing register-level interfaces with silicon teams.
Demonstrated, hands-on AI-assisted engineering proficiency, plus the judgment to validate what the AI produces.

Preferred Qualifications

RISC-V firmware and toolchain experience.
Firmware orchestration for multi-core accelerator arrays.
Hardware root-of-trust ecosystems (e.g., Caliptra) and SHA-2/signature verification.
Code-generation toolchains (SystemRDL, Kaitai, CMake) and simulator-based co-verification.
Familiarity with emerging AI/HPC interconnect standards: Ultra Ethernet (UEC), UALink, and ESUN.
Background in HPC/AI networking, RDMA, or libfabric.

Location:

Remote: This role fully supports remote work for employees residing within the United States.

We offer a competitive compensation package that includes equity, cash, and incentives, along with health and retirement benefits. Our dynamic, flexible work environment provides the opportunity to collaborate with some of the most influential names in the semiconductor industry.

At Cornelis Networks your base salary is only one component of your comprehensive total rewards package. Your base pay will be determined by factors such as your skills, qualifications, experience, and location relative to the hiring range for the position. Depending on your role, you may also be eligible for performance-based incentives, including an annual bonus or sales incentives.

In addition to your base pay, you’ll have access to a broad range of benefits, including medical, dental, and vision coverage, as well as disability and life insurance, a dependent care flexible spending account, accidental injury insurance, and pet insurance. We also offer generous paid holidays, 401(k) with company match, and Open Time Off (OTO) for regular full-time exempt employees. Other paid time off benefits include sick time, bonding leave, and pregnancy disability leave.

Cornelis Networks does not accept unsolicited resumes from headhunters, recruitment agencies, or fee-based recruitment services. Cornelis Networks
is an equal opportunity employer, and all qualified applicants will receive consideration for employment without regard to race, color, religion, sex, sexual orientation, gender identity or expression, pregnancy, age, national origin, disability status, genetic information, protected veteran status, or any other characteristic protected by law. We encourage applications from all qualified candidates and will accommodate applicants’ needs under the respective laws throughout all stages of the recruitment and selection process.

About the company

Cornelis Networks builds high-performance AI and HPC networking fabrics to help accelerators and servers in data centers exchange data with less idle GPU time. Its open architecture works across different GPUs and accelerators, avoiding vendor lock-in and not relying on a single full-stack solution. The company began shipping products after spinning out of Intel in 2020 and is developing a next-generation fabric. Its current push includes Active Compute Fabric, a networking technology that lets chips process and send information concurrently, aimed at enabling closer integration of compute and communication. The goal is to commercialize the platform, expand adoption, and challenge closed AI networking stacks by offering an open, multi-vendor fabric that improves data movement in AI/HPC clusters.

Company Size

201-500

Company Stage

Late Stage VC

Total Funding

$335.8M

Headquarters

Tredyffrin Township, Pennsylvania

Founded

2019

Get referred to Cornelis Networks

See people who can refer or advise you

Simplify's Take

What believers are saying

Cornelis raised $205 million on September 14, 2026, extending runway and scale.
Qualcomm collaboration and AMD reference architectures broaden credibility with rack-scale buyers.
NEC, xFusion, and TACC partnerships expand global deployments across Japan, Europe, and U.S. science.

What critics are saying

Nvidia’s integrated networking and software stack keeps locking hyperscale AI buyers.
CN6000 targets Q4 2026; any slip delays revenue while rivals ship faster.
Without enough design wins, Cornelis stays capital-intensive and becomes an acquisition target.

What makes Cornelis Networks unique

Cornelis’ open Omni-Path fabric runs across Nvidia, AMD, and Intel clusters.
Active Compute Fabric puts programmable compute inside the network, cutting idle accelerator time.
CN5000 deployments at TACC and LLNL validate production performance on real supercomputers.

Help us improve and share your feedback! Did you find this helpful?

Benefits

Flexible Work Hours
Remote Work Options
Paid Holidays
Company Equity
Health Insurance
Dental Insurance
Vision Insurance
Disability Insurance
Life Insurance
Health Savings Account/Flexible Spending Account
Pet Insurance
401(k) Company Match

Growth & Insights and Company News

Headcount

6 month growth

1 year growth

2 year growth

Techflier

Sep 14th, 2026

Pennsylvania's Cornelis Networks takes $205M for in-network compute.

Pennsylvania's Cornelis Networks takes $205M for in-network compute. The Pennsylvania AI networking challenger has raised $205M and launched an Active Compute Fabric that moves programmable compute inside the network. Last updated: September 14, 2026 11:16 pm Every accelerator in a large AI cluster spends part of its life waiting for data it cannot fetch fast enough. Cornelis Networks has banked $205M led by IAG Capital Partners, pairing the raise with a Qualcomm collaboration and a new architecture called Active Compute Fabric. The Wayne, Pennsylvania company builds congestion-free networking for AI and HPC clusters, taking on Cisco and Arista. Deployments include the Texas Advanced Computing Center and the US Department of Energy. Active Compute Fabric, unveiled at the AI Infra Summit, integrates programmable compute directly into the network. The aim is to offload collective operations so expensive accelerators spend less time idle waiting for data, which matters as training clusters grow past hundreds of thousands of chips. CEO Lisa Spelman said the funding scales production, deepens customer partnerships and accelerates the rollout of the CN6000 platform. Compute, memory and storage all became workload-aware in recent years while traditional networks lagged, leaving a gap Cornelis is attacking with in-network processing. Why it matters: at current cluster sizes, networking decides how much of the hardware customers already paid for actually gets used.

IntelPro

Sep 14th, 2026

AI infrastructure company Cornelis raises $205M to chip away at Nvidia s dominance.

AI infrastructure company Cornelis raises $205M to chip away at Nvidia s dominance. The company also announced a product called Active Compute Fabric, a network technology that targets the fact that much GPU time is wasted waiting for Cornelis, a company creating networking technology to help AI chips communicate more effectively, announced Monday that it has raised $205 million in a funding round led by IAG Capital Partners. It also announced a product called Active Compute Fabric, a network technology that targets the fact that much GPU time is wasted waiting for data to arrive. Cornelis hopes to address this with a networking fabric that lets chips process and send information at the same time. The company, which spun off from Intel in 2020, is competing with Nvidia by offering an open architecture, meaning customers can use a variety of GPU and accelerator hardware with Cornelis' networking fabric. Though Nvidia chips can technically run on other networking fabrics, they're optimized to run on Nvidia's own software, making it much easier - and more enticing - for customers to use Nvidia's full GPU stack. Cornelis is part of a new wave of AI infrastructure companies emerging to break apart Nvidia's market dominance, piece by piece (or chip by chip, one could say). Cornelis has already started shipping its product and is working on a new generation of it, expected to be released later this year.

SiliconANGLE Media

Sep 14th, 2026

Cornelis Networks raises $205M for Active Compute Fabric to cut AI network traffic by 50%

Cornelis Networks has raised $205 million in funding led by IAG Capital Partners and launched its Active Compute Fabric architecture for AI workloads. The data center infrastructure startup also announced a strategic collaboration with Qualcomm Technologies. The Active Compute Fabric integrates programmable compute directly into the network, performing workload-specific operations as data moves through the system. This approach can reduce overall network traffic by up to 50%, according to pre-production simulations. The architecture addresses bottlenecks that leave AI accelerators idle whilst waiting for data. Built on open standards including Ethernet, UALink, and Ultra Ethernet, the fabric can adapt in real time, offload complex operations, and work with existing compute architectures. Cornelis will use the funding to scale production of its CN5000 and CN6000 network switches and accelerate Active Compute Fabric deployment.

HPCwire

Aug 20th, 2026

Cornelis and NEC Expand Collaboration to Advance AI and HPC Infrastructure in Japan.

Cornelis and NEC Expand Collaboration to Advance AI and HPC Infrastructure in Japan. August 20, 2026 Press play to listen to this content WAYNE, Pa. and TOKYO, Aug. 20, 2026 - Cornelis and NEC Corporation have announced an expanded collaboration that builds on the companies' successful work together in Europe and will help organizations across Japan and the broader Asia-Pacific region deploy next-generation AI and high-performance computing (HPC) infrastructure using Cornelis high-performance networking solutions. The expanded collaboration builds on NEC's successful evaluation of the Cornelis CN5000 Omni-Path platform and the companies' existing collaboration in Europe, creating a foundation to support enterprise AI, manufacturing, research, and high-performance computing deployments across Japan. As part of the collaboration, NEC also plans to participate in early evaluation activities for the next-generation Cornelis CN6000 platform, helping customers prepare for increasingly complex AI and HPC workloads. "AI infrastructure is placing unprecedented demands on network performance, scalability, and efficiency," said Lisa Spelman, CEO of Cornelis. "NEC's extensive experience delivering enterprise and HPC infrastructure throughout Japan makes them an outstanding partner as we continue giving customers more choice and bringing advanced networking technologies to new markets. Together, we're helping customers build AI and HPC environments that deliver greater performance today while preparing for the next generation of large-scale computing." The collaboration reflects growing adoption of open, high-performance networking alternatives as AI and HPC deployments continue to scale. Following a comprehensive technical evaluation of the CN5000 platform, NEC and Cornelis will continue collaborating to support customer opportunities by leveraging NEC's long-standing relationships with enterprise, manufacturing, academic, and research organizations throughout Japan. NEC's evaluation included extensive MPI communication testing across multiple workloads and communication patterns, validating the capabilities of the CN5000 platform while also identifying optimization techniques that further improve application performance. The joint evaluation demonstrated the value of close engineering collaboration to help customers maximize networking efficiency across large-scale HPC environments. The companies also plan to extend their collaboration to the upcoming Cornelis CN6000 platform, allowing NEC to evaluate next-generation networking technologies as customers prepare for larger AI training, inference, and HPC deployments. "Organizations across Japan are preparing for increasingly complex AI and HPC environments that require higher performance, scalability, and efficiency," said Takeshi Hirose, Senior Director of Compute Department, NEC Corporation. "Our collaboration with Cornelis broadens the high-performance networking technologies available to our customers while allowing us to evaluate next-generation capabilities that support future computing requirements." The collaboration further strengthens Cornelis' growing global ecosystem of infrastructure partners, enabling customers to deploy high-performance networking through trusted server and infrastructure providers while benefiting from continued innovation across the Cornelis product portfolio. As AI clusters continue to scale, Cornelis and NEC will continue working together to evaluate new networking technologies, optimize customer deployments, and support future AI and HPC infrastructure across Japan and beyond. About Cornelis Cornelis delivers high-performance, scale-out networking solutions that accelerate AI and HPC workloads. Built on the powerful Omni-Path architecture, Cornelis technology enables lossless, congestion-free networking that reduces training time, improves inference, and maximizes compute utilization. From foundation model training to complex climate modeling and real-time analytics, Cornelis' solutions power the most demanding workloads across commercial, academic, government and cloud environments. With a focus on performance, scalability, and efficiency, Cornelis helps organizations achieve faster insights and greater return on infrastructure investments. Learn more at cornelis.com. About NEC Corporation The NEC Group leverages technology to create social value and promote a more sustainable world where everyone has the chance to reach their full potential. NEC Corporation was established in 1899. Today, the NEC Group's approximately 110,000 employees utilize world-leading AI, security, and communications technologies to solve the most pressing needs of customers and society. For more information, please visit https://www.nec.com. Deep Origin this month announced that its AI drug discovery framework delivered nearly a 31%... AI models are getting better at a rapid pace. They are now able to reason,... The tech industry is fixated on one main metric, the raw number of GPUs accumulated... Scientists running large simulations can end up with terabytes of data that then has to... Jensen Huang believes NVIDIA's chips are becoming much more than expensive pieces of hardware. As... As hybrid cognition deepens, the boundary between biological and artificial embodiment will begin to blur...

Cornelis Networks

Jul 29th, 2026

Get more from your 400 Gb/s fabric: lessons from Lenovo's Cornelis CN5000 validation. July 29th, 2026 Paul Stasurak, Cornelis-Lenovo Solutions Key takeaways: * Get more value from a 400 Gb/s fabric investment: Lenovo measured 378-391 Gb/s across tested node pairs, averaging 385 Gb/s - nearly 100% of the nominal line rate. * Accelerate communication-intensive HPC and AI workloads: The validated configuration delivered node-to-node latency as low as approximately 1.1 μs on Lenovo ThinkSystem SC750 V4 servers powered by Intel Xeon 6 processors. * Reduce deployment risk and time spent tuning: Lenovo's LP2474 guide documents the tested firmware, Fabric Manager, cabling, and MPI settings, giving teams a validated starting point instead of a blank page Make every bit of your 400 Gb/s HPC network count. When you invest in a 400 Gb/s fabric, the gap between "installed" and "optimized" is measured in real money - idle CPU cores, longer job queues, and fewer HPC simulations completed per day. A fabric running at 70% of its potential quietly taxes every workload on the cluster. Getting deployment and tuning right the first time is what turns a capital purchase into sustained scientific output. This isn't theory. Lenovo's EveryScale team validated the full deployment in their HPC Benchmarking Centre on ThinkSystem SC750 V4 servers powered by Intel Xeon 6 processors - a real cluster, real cables, and real benchmarks. A fast network can still underperform. A high-performance interconnect is only as fast as its weakest configuration step. A firmware level that's slightly off, a cable on the wrong switch port, or an MPI stack left at defaults can silently cost 10-20% of your performance. And because the loss is invisible without careful benchmarking, most teams never know it's there. The last mile to an efficient HPC cluster. CN5000 is a complete 400 Gb/s end-to-end Omni-Path fabric with credit-based flow control, fine-grained adaptive routing, delivered on an end-to-end network of SuperNICs and Switches built for over 800 million messages per second. But raw capability has knobs. A dual-socket, 128-core node defaults to 208 MPI contexts - not enough to feed every core without context sharing. Cable length dictates which switch ports deliver latency-optimized links. The fabric manager needs the right port and adapter configuration to sweep the fabric cleanly. None of these are defects; they're the settings that decide whether you get spec-sheet performance or something less. From high-speed hardware to a tuned HPC system. Cornelis doesn't hand you hardware and walk away. Together with Lenovo, Cornelis Networks publish experience-based best-practice guides drawn from real deployments - pairing the open Cornelis OPX (Omni-Path Provider) software stack with documented, repeatable tuning. OPX is OpenFabrics-compliant and built on OFI/libfabric, so it runs Open MPI, MPICH, MVAPICH, and NCCL/RCCL with no application rewrites. The tunables that matter - MPI context sharing, bulk transfer service, and SDMA - are spelled out, not left to guesswork. Its goal is simple: help you squeeze every ounce of value from the network you already paid for, so your cluster is not held back by the network. What Lenovo measured on ThinkSystem servers. The proof, straight from the Lenovo benchmarking center: * Bandwidth: 378-391 Gb/s measured across all node pairs (averaging 385 Gb/s) - roughly 96% of the 400 Gb/s line rate. * Latency: as low as ~1.1 microseconds node-to-node, delivering one of the industry's lowest end-to-end latency for cluster networking * Repeatability: every firmware level, command, and tunable is documented against Lenovo's tested "best recipe." The advantages of CN5000 expand beyond what Lenovo specifically tested. CN5000 SuperNICs are engineered for 800M+ messages per second - the currency of MPI collectives and AI communication and the OPX stack (OFI/libfabric) run today's MPI and AI libraries with no application rewrites. Evaluate the deployment, not the spec sheet. When you evaluate an HPC fabric, look past the peak numbers on the spec sheet and ask what happens after the purchase order. Does the vendor publish validated reference architectures and tested firmware "best recipes"? Is the software stack open and compatible with your existing MPI and AI libraries? And are the performance tunables documented and matched to your CPU SKU - since core count, sockets, and cabling all change the right settings? The answers determine how much of that 400 Gb/s you'll actually use. How to get started. Leverage the full guide, written by networking experts. Lenovo's "Installation and Best Practices for Implementing Cornelis CN5000 Omni-Path on Lenovo ThinkSystem Servers" (Lenovo Press, LP2474) walks through the entire deployment step by step. Then talk to the Cornelis team about bringing the same confidence to your own cluster.

Cornelis Networks

Principal Embedded Firmware Engineer - AI/HPC Networking Silicon

About the job

About the company

Get referred to Cornelis Networks

Simplify's Take

What believers are saying

What critics are saying

What makes Cornelis Networks unique

Benefits

Growth & Insights and Company News

6 month growth

1 year growth

2 year growth