2 months ago
Pune, IndiaMid Level
Responsibilities
- Partner with software, research, architecture, and product teams to align technical strategies and grow the AI ecosystem on RTX and DGX PCs.
- Build and optimize local AI inference stacks for RTX, RTX Pro, and DGX GPUs across different hardware architectures.
- Architect and develop inference runtimes and execution stacks for LLM, vision-language, TTS, ASR, and diffusion workloads.
- Optimize AI models, data pipelines, and inference runtimes using quantization, pruning, sparsity, and distillation.
- Develop performance and accuracy sweep infrastructure, perform system-level debugging, analyze trade-offs, and drive fixes toward production readiness.
Requirements
- 2+ years of experience and a bachelor's, master's, or PhD in Computer Science, Software Engineering, Mathematics, or a related field, or equivalent experience.
- Excellent C++ programming and debugging skills with strong knowledge of data structures, algorithms, and machine learning.
- Proven experience with AI inference pipelines and applications using frameworks such as Llama.cpp, vLLM, PyTorch, WinML, DXCGC, and TensorRT.
- Deep interest in inference backends and runtime internals, including scheduling, memory management, KV-cache behavior, graph execution, quantization, and hardware-aware optimization.
- Strong analytical, problem-solving, multitasking, written communication, and oral communication skills.
- Preferred qualifications include knowledge of modern machine learning, deep neural networks, and generative AI; open-source contributions; end-to-end product delivery; CUDA and lower-level GPU programming; and experience with Vulkan and DirectX.
Benefits
- The posting mentions competitive salaries and a generous benefits package.
- The employer is an equal-opportunity employer that values diversity.
Categories
About Nvidia
Nvidia designs and sells GPUs and accelerated computing platforms for data centers, AI/ML, graphics, gaming, and automotive, monetizing through hardware, software platforms (CUDA, AI frameworks), and systems like DGX and networking. Customers include cloud providers, enterprises, researchers, and OEMs. Founded in 1993 and headquartered in Santa Clara, it is a public company traded on NASDAQ under NVDA.