Top Tech Jobs & Startup Jobs in Austin, TX

Lead alignment of NVIDIAcompiler codebases with open-source projects, build tooling and workflows to improve developer productivity, automate rebasing/patch management and apply AI-assisted workflows, while partnering with architecture and CI teams to scale changes across NVIDIA.

Lead pre-silicon system software bring-up and validation on simulation platforms. Develop automation, tools, and workflows to improve simulation-based development, debug complex cross-stack issues, enable teams to use virtual platforms, and drive platform readiness for new chips in early-development environments.

Develop and implement compiler optimization algorithms for deep learning workloads, analyze networks, debug and profile GPU performance (CUDA), define public APIs, and deliver ahead-of-time and just-in-time compilation techniques for NVIDIA GPUs to improve inference performance, build times, and memory efficiency.

Provide technical support to NVIDIA Enterprise customers by triaging and resolving issues, working with engineering on reproductions/logs, applying AI/ML and agentic AI to build support tools and products, documenting interactions and knowledge, and owning cases to resolution (occasional weekend/holiday support).

Provide advanced support and root-cause analysis for NVIDIA networking technologies in AI clusters. Reproduce and resolve customer issues, develop fixes and tools, analyze performance/tuning for high-performance lossless networks, collaborate with R&D and customers, and occasionally support outside regular hours.

Design and implement GPU performance analysis and profiling capabilities for NVIDIA hardware, drivers, and SDKs. Analyze chip features, prototype and refine data collection methods, collaborate with architects and developer tools engineers, and ensure observability of critical performance behaviors for next-generation GPUs and SoCs.

The role involves designing and developing VLSI CAD software, collaborating in agile practices, and advancing design tools for chip development.

Design and build a scalable failure-attribution framework for heterogeneous CPU/GPU clusters: collect high-fidelity telemetry, implement low-overhead tracing, automate root-cause classification (hardware, software, environment), and enable proactive resiliency measures like migration or checkpointing.

Lead technical vision and strategy for next-generation graphics developer tools. Design and prototype tooling, drive cross-team initiatives, mentor engineers, engage external developers and partners, and deliver production-ready solutions that improve graphics development, debugging, profiling, and optimization workflows.

Design and optimize CUDA kernels and cluster-scale distributed systems for deep learning. Prototype system and compiler optimizations, profile hardware-software interactions, collaborate with researchers and architects, and deliver high-performance runtime tools and maintainable code for training and inference at scale.