Top Tech Jobs & Startup Jobs

Develop and execute product-level reliability qualification plans for advanced-node ICs and packaged devices. Collaborate with design, packaging, test, and product teams to validate reliability stress tests, analyze failures and failure mechanisms, build failure models, drive corrective actions, maintain reliability databases, and produce qualification reports and presentations.

Design and implement Rust-to-GPU compiler backends, IR frameworks, and JIT/AOT toolchains. Lower Rust AST/MIR to MLIR/LLVM/PTX, build GPU-specific optimizers, enforce safe parallel abstractions across host/device boundaries, and expose ergonomic device-side primitives. Drive projects from research to production and support profiling, debugging, and benchmarking workflows.

Lead distributed engineering and data teams to build NVIDIA's end-to-end data curation strategy for autonomous vehicles. Architect scalable systems and pipelines to mine, classify, and surface valuable driving scenarios from massive real and simulated datasets. Collaborate with research, perception, mapping, simulation, and fleet teams to deliver high-quality data, champion metadata and quality standards, and drive continuous AV performance improvements.

Design and optimize low-latency C/C++ systems for real-time streaming over 5G, Wi‑Fi, and other wireless networks. Integrate with cellular and platform APIs, analyze packet captures and telemetry to fix latency and packet loss, develop KPIs and test frameworks, build realistic wireless simulations, and partner with cloud, automotive, carrier, and platform teams to deliver scalable connectivity solutions.

Design, build, and optimize production-quality systems for interactive world models, simulation, rendering, and real-time GPU inference. Integrate generated worlds, reconstructed scenes, and evaluation loops into scalable, reliable end-to-end systems while collaborating across research and product teams to move prototypes to production.

Analyze and reduce RTL and pre‑silicon power for GPUs and networking chips using EDA tools and AI/ML. Run workloads, perform comparative power analysis, prototype Verilog features, debug power anomalies, and collaborate with architects, RTL designers, and physical design teams to drive power improvements.

Lead architecture and optimization of deep learning inference for autonomous driving platforms. Drive end-to-end performance analysis across models, compiler/runtime (TensorRT/Triton), CUDA kernels, memory and scheduling. Develop model optimization techniques (quantization, pruning, fusion), build profiling and benchmarking tools, and collaborate with platform, perception, safety, and silicon teams to deploy efficient, reliable DNNs on NVIDIA automotive compute platforms.

The role involves driving the adoption of NVIDIA Omniverse, collaborating with partners on technical solutions, and providing support to overcome integration challenges while engaging at all levels.

Lead performance and scalability analysis of the Kubernetes-based accelerated runtime stack, design upstream control-plane changes for hyperscale clusters, optimize container startup and inference latency, advance confidential container performance, model large AI-factory deployments with simulations, build at-scale tests and monitoring, and collaborate with researchers and upstream communities to validate and publish results.

Responsible for analyzing memory supply requirements and purchases, collaborating with supply chain teams, enhancing planning processes, and driving operational efficiency.