Top Tech Jobs & Startup Jobs

Develop algorithms and optimizations for inference and compiler stack, enhance performance metrics, collaborate with hardware teams, and publish work on novel approaches.

Conduct fundamental research on novel large-scale generative AI methods, particularly for biomolecular and scientific applications. Design and implement models, publish original research, collaborate with research and product teams, present at conferences, and transfer technology to products. The role requires strong mathematical foundations, generative AI expertise, scientific data modeling experience, programming skills, deep learning framework knowledge, and a strong research record.

Lead global partner marketing for NVIDIA's Enterprise ISV ecosystem: develop and execute co-marketing plans, demand-generation campaigns, events, content, and digital marketing; coordinate with Product, Sales, and BD; supervise execution and ROI, and build trusted partner relationships to amplify solutions on NVIDIA technology.

Lead data-center power systems architecture, modeling, simulation, validation, risk management, and vendor coordination for rack-level power programs. Drive designs from concept through production, analyze failures, optimize efficiency and reliability, translate requirements into milestones, and align architecture, validation, mechanical, firmware, compliance, and supplier teams.

Design and implement an LLVM-based JIT backend for NVIDIA GPUs, develop compiler passes and optimizations to meet performance and compile-time targets, collaborate with hardware and application teams to resolve issues, apply modern compiler technologies, and influence future GPU architectures.

The role involves architecting and operating NVIDIA's cloud-native attestation platform, developing high-availability services, collaborating with cross-functional teams, and mentoring engineers.

Design, implement, test, and debug low-level NVIDIA software for GPU bring-up, emulation, and product hardening. Work with kernel, architecture, system design, and manufacturing teams to move hardware from development to production and address system-level issues affecting OEMs and end users.

Design and implement an LLVM-based backend JIT compiler for NVIDIA GPUs. Develop compiler passes and optimizations, focusing on high performance and low compile time. Collaborate with hardware, compiler, and application teams to resolve issues and influence future GPU architectures.

Support installation and customization of foundry techfiles, debug design/tool/techfile errors, maintain and support EDA/CAD tools (Virtuoso, IC-Manage, DRC/LVS, extraction, SPICE), work with vendors, and develop automation scripts and infrastructure using Perl, Cadence SKILL, and C++ to improve custom circuit designer productivity.

The role involves designing and optimizing GPU architectures for AI Inference, analyzing hardware-software relationships, and developing performance models.