Top Tech Jobs & Startup Jobs in Boston, MA

Verify ASIC/GPU and SoC designs using advanced verification methodologies. Define verification scope, develop test plans and test generators, build verification infrastructure, and collaborate with architects, designers, and pre/post-silicon teams to validate CPU/GPU interactions and memory coherence.

Develop and support high-performance infrastructure tools for chip design and verification. Build scalable backend and frontend web applications using Golang, TypeScript, and JavaScript; manage hardware-level product definitions; improve workflows for architecture, hardware, and software teams; and research solutions that increase engineering efficiency.

Perform RTL-to-gate synthesis and QoR convergence for complex digital blocks, optimize synthesis strategies and constraints, analyze and resolve QoR regressions, support physical implementation from floorplanning through timing closure, and automate setup, execution, reporting, and issue triage across teams.

Lead architecture and specification of chip-to-chip interconnects (NVLink), collaborate with research, architects, and design teams, create architectural models and documentation, drive implementation across design/verification/firmware/software, and define NVLink fabric, network configuration, and management flows throughout product lifecycle.

Research and develop AI-native numerical algorithms that combine machine learning with scientific and engineering solvers. Build solver-in-the-loop pipelines, learned preconditioners, AI-guided multigrid methods, differentiable solver components, and hybrid ML/numerical methods. Evaluate convergence, stability, accuracy, robustness, failures, resource use, and performance. Collaborate across NVIDIA Research, GPU computing, simulation, engineering, semiconductor, and digital twin teams while shaping the applied research agenda.

Create and deliver developer-focused technical content and workshops that teach CUDA and NVIDIA GPU technologies. Evaluate new CUDA features, produce tutorials and blog posts, capture developer feedback to inform product decisions, and collaborate across product, engineering, and marketing teams to drive developer adoption.

Design and optimize high-performance C++/CUDA libraries for GPU-based data processing. Improve multi-node GPU communication (UcxExchange), optimize Presto GPU query performance, and lead enhancements across Presto, Velox, and cuDF projects for efficient DataFrame and database acceleration.

Drive the development and roadmap of HPC and AI/ML products for physics, plasma, high-energy-density simulations, and resilient materials discovery. Define features, requirements, positioning, and go-to-market strategy; collaborate with engineering and NVIDIA software teams; identify customers and partnerships; and represent products at workshops and conferences.

Build and lead development of NVIDIA’s open-source NeMo Core Platform for executing, evaluating, deploying, and optimizing agentic AI systems across local, Docker, Kubernetes, Slurm, on-premises, and air-gapped environments. Design platform APIs, plugins, SDKs, job orchestration, authentication, RBAC, observability, testing, and reliability features. Provide technical leadership through architecture and code reviews, mentoring, and ownership of complex cross-component problems.

Lead NVIDIA’s RL post-training frameworks strategy and engineering ecosystem across distributed training, inference, rollout, evaluation, orchestration, and NVIDIA platforms. Build and manage globally distributed teams, prioritize upstream and internal investments, establish benchmarks and execution metrics, and drive reliable open-source integrations. Partner with research, product, hardware, CUDA, networking, and external communities to scale reinforcement learning workloads across GPUs and heterogeneous systems.