Jobs at Cornelis Networks

Design and implement advanced Ethernet protocols for next-generation ASICs used in AI and high-performance computing networks. Responsibilities include writing microarchitecture specifications, defining RTL timing constraints, collaborating with physical design and verification engineers on timing optimization and test coverage, and debugging post-silicon issues with hardware, firmware, and software teams.

Optimize distributed AI training and inference across CPU/GPU clusters, networking silicon, and software stacks. Benchmark workloads, tune distributed serving and training architectures, analyze communication and system bottlenecks, validate RDMA and collective performance, and create customer-facing proof points. Use profiling and observability tools to visualize performance, compare interconnects, and communicate best practices through technical documentation, publications, and customer engagements.

Lead verification closure for complex ASICs, SoCs, and networking hardware. Define verification strategies, develop UVM testbenches, create functional tests, debug RTL failures, and close functional and code coverage. Collaborate with design, software, emulation, hardware, and silicon validation teams. Guide and mentor verification engineers while establishing coding and verification standards and applying AI tools to improve team productivity.

Architect and develop bare-metal C firmware for RISC-V management cores controlling AI/HPC networking acceleration engines. Responsibilities include secure firmware loading, image authentication, boot and reset sequencing, health validation, multi-die firmware distribution, updates, hardware/software interface definition, simulator-based testing, architecture standards, code reviews, and technical mentorship.

Drive planning and execution of software initiatives for HPC and AI networking products. Manage schedules, milestones, dependencies, releases, risks, dashboards, and decision records while coordinating software, firmware, hardware, platform, validation, product, and field teams. Support release readiness, customer-impacting issue resolution, prioritization, and engineering-process improvements. Communicate progress and tradeoffs to technical teams, executives, and customer-facing stakeholders.

Owns and grows strategic UK enterprise, public sector, academic, OEM, and partner relationships for AI and HPC networking solutions. Responsibilities include executing direct sales strategies, prospecting, managing CRM pipelines, closing complex partnerships, presenting solutions, collaborating with channel and OEM teams, leveraging technical ecosystems, and providing market feedback. The role requires a proven technology sales record, strong HPC and AI ecosystem expertise, and approximately 50% EMEA travel.

Administer GitHub, Jira, Confluence, AWS, and engineering lab systems; manage permissions, workflows, access, infrastructure operations, automation, and developer support. Maintain Linux-based lab environments, troubleshoot AWS and system access issues, document procedures, and coordinate with engineering, program management, IT, DevOps, and onsite personnel. The role requires reliable execution of routine administration, clear communication, and escalation of architectural or high-risk changes.

Own and grow Cornelis Networks’ strategic relationship with Lenovo. Develop account plans, lead QBRs and executive engagements, identify co-selling opportunities, coordinate joint go-to-market initiatives, forecast revenue in Salesforce, and represent the company at events. The role requires expertise in AI/HPC ecosystems, OEM partnerships, enterprise sales, interconnect technologies, and cross-functional stakeholder influence. This remote U.S. position requires 50% travel, with preference for Raleigh-area candidates.

Design and implement RTL for high-speed ASIC data paths and packet-processing logic using Verilog and SystemVerilog. Collaborate on verification, timing constraints, physical design, post-silicon validation, system debugging, and power-aware performance optimization for AI and HPC networking systems.

Develop and maintain AI-based ASIC verification automation flows, regression infrastructure, dashboards, reporting tools, and triage automation. Build scripts and integrations using Python, Perl, Tcl, shell scripting, and Make. Support simulation, coverage, lint, formal, emulation, continuous integration, EDA tool integration, and distributed compute infrastructure. Debug automation, tool, runtime, licensing, queue, and workflow issues while improving verification reliability, reproducibility, and efficiency across geographically distributed engineering teams.

Lead and grow the RTL design engineering team responsible for next-generation networking ASICs. Own RTL delivery schedules, coordinate design verification, emulation, and physical design dependencies, manage timing-closure and tape-out readiness, identify schedule risks, and allocate resources. Develop headcount and organizational plans, lead hiring, and scale globally distributed engineering practices while contributing hands-on expertise in microarchitecture, RTL design, synthesis, verification, and PPA optimization.

Verify RTL for advanced ASICs and SoCs at block, unit, and system-on-chip levels. Develop UVM testbenches, write and execute verification tests, analyze functional and code coverage, perform block-level formal verification, and support post-silicon verification. The role requires validating complex SoCs with multiple clock and reset domains and using scripting languages for verification automation.

Lead end-to-end PCIe IP integration into complex ASIC and SoC designs, collaborating across architecture, verification, physical design, software, and external IP vendors. Optimize PCIe performance, contribute to IO and interconnect architecture, and lead silicon bring-up, interoperability testing, and debugging across RTL, gate-level, emulation, and post-silicon environments. Mentor engineers and establish PCIe subsystem development practices for high-performance AI and HPC platforms.

Lead verification closure for complex ASICs and SoCs used in AI and high-performance computing networking. Define verification strategies, develop UVM/SystemVerilog testbenches, execute functional testing, debug RTL failures, and close functional and code coverage. Guide block, subsystem, and SoC verification while collaborating with design, software, emulation, hardware, and post-silicon teams. Mentor engineers, establish verification guidelines, and promote AI tools to improve team productivity.

The Senior Account Manager will develop and execute sales strategies for HPC and AI networking solutions across higher education and automotive accounts. Responsibilities include prospecting, building customer relationships, managing Salesforce pipeline activity, meeting quotas, collaborating with channel and OEM partners, presenting technical solutions, and providing market feedback. The role requires a self-generating hunter mentality, grant proposal experience, technical knowledge of network interconnects, and up to 50% travel for conferences and customer meetings.

Design and optimize AI communication middleware for distributed multi-node, multi-GPU training. Implement C/C++ performance-critical features, improve GPU communication paths, profile and tune frameworks (PyTorch, TensorFlow, JAX, DeepSpeed), develop benchmarks, contribute upstream, and collaborate with kernel, driver, switch, and systems teams to validate and deploy high-performance networking for AI/HPC.

Design, develop, and upstream-enable AI/HPC communication middleware (MPI/SHMEM, NCCL/RCCL). Integrate middleware with transports (libfabric/UCX/verbs), optimize performance, collaborate across kernel/driver and switch teams, analyze performance traces, reproduce and fix customer issues, and contribute to open-source projects.

Develop and optimize AI/HPC communication middleware (MPI/SHMEM, CCL/NCCL/RCCL) over Cornelis interconnects; integrate with transports (libfabric/OFI, UCX), contribute upstream open-source, collaborate across kernel/driver and switch teams, and analyze performance traces to reproduce and fix customer issues.

Design and develop system and PCB architectures from concept through production for high-performance networking platforms. Select components, create schematics and design files, support layout, debug system-level issues, assist software integration, and support testing, compliance, and manufacturing transfer.

Design, implement, and operate a private, secure AI platform and autonomous agent workforce for engineering workflows. Build agents (FastAPI/CLI/chat), integrate MCP and RAG, maintain containerized infrastructure, CI/CD validation, secrets and cost management, and enterprise integrations (GitHub, Jira, Confluence, Teams). Continuously evaluate models, improve agent reliability, and drive platform adoption across low-level systems engineering domains.