Top Tech Jobs & Startup Jobs

Design, architect, develop and debug native and para-virtualized Linux/QNX device drivers and Android HALs for NVIDIA DRIVE OS. Troubleshoot system-level issues, lead software architecture discussions, gather requirements, coordinate cross-functional teams, and participate in feasibility, safety evaluations, and product lifecycle activities to integrate DRIVE solutions into automotive platforms.

Design, build, and deliver scalable SAP IBP planning solutions (response & supply, demand). Support and enhance planning processes, prototypes, integrations, dashboards, and end-to-end material, supply, replenishment, deployment, and service-parts planning to improve profitability and operational performance.

Design, implement, and optimize GPU-accelerated deep learning kernels, kernel libraries, and inference runtime components. Build production-quality software (e.g., cuDNN, FlashInfer) and JIT/codegen systems, profile and tune performance for LLM inference, and collaborate across compilers, GPU architecture, and open-source ecosystems to ship scalable AI inference solutions.

Lead risk-based internal audit coverage for Order-to-Cash, Legal & Regulatory Compliance, and Human Resources. Design and execute audits on revenue controls, trade compliance, anti-bribery, data privacy, antitrust, payroll/compensation, and HR controls. Provide independent assurance, actionable insights to executives and the Audit Committee, and maintain a dynamic risk-based audit plan aligned with ERM and SOX.

Lead GeForce consumer sales through AIC/OEM partners and distributors. Develop channel strategies, manage forecasts, promotions, inventory and distributor performance, drive demand generation, events, partnerships, and advocacy to grow branded product sales and market share.

Analyze, profile, and optimize deep learning training workloads on NVIDIA GPUs; implement production-quality software across drivers to DL frameworks; build processor/system simulators and automation tools to enable architecture studies and workload optimization.

Lead failure analysis and debug of datacenter DGX/MGX/HGX systems during mass production. Diagnose HW/SW/FW issues across boards, systems, and racks, run experiments, collect/analyze data, enable DFx, provide root-cause and corrective actions, write reports and debug guides, and coordinate with vendors, factories, and partner teams worldwide.

Design GPU boot, PCIe/CXL enumeration, and capability-discovery architecture. Develop functional and performance models in C++, create validation test plans, coordinate with software, hardware, and verification teams, and support post-silicon validation. The role requires a computer architecture, computer science, or electrical engineering background, systems coursework, hardware/software interaction knowledge, and strong C++ proficiency. Familiarity with advanced interconnects, scripting, security, encryption, RISC-V, or microcode is advantageous.

Develop and optimize C++ and CUDA libraries for GPU-accelerated data processing, distributed query engines, warehouse and Lakehouse workloads. Responsibilities include improving data loading, parsing, joins, aggregations, I/O, memory management, concurrency, and storage-to-compute paths. The role partners with Sales and Developer Relations on integrations and production issues, contributes to architecture and delivery, and drives performance optimization across storage, networking, and CPU/GPU systems.

Build and operate NVIDIA’s serverless AI inference platform across globally distributed, GPU-backed Kubernetes clusters. Lead feature implementation, testing, performance optimization, reliability improvements, customer issue resolution, reference architecture development, and technology evaluation. Mentor engineering teams on scalable AI/ML workloads and contribute to product requirements and roadmap development.