NVIDIA, the global leader in GPU computing and AI innovation, is inviting applications for the role of System Software Engineer – Local AI in Pune, India.
This opportunity is designed for engineers with 2+ years of experience who want to work on on‑device AI software, inference runtimes, GPU optimization, and edge deployment. The role is part of NVIDIA’s LocalAI team, which focuses on delivering AI models locally to reduce latency, improve real‑time processing, and enhance privacy.
Job Overview
| Details | Information |
|---|---|
| Company | NVIDIA |
| Role | System Software Engineer – Local AI |
| Job ID | JR2022875 |
| Location | Pune, India |
| Category | Engineering |
| Job Type | Full‑Time |
Key Responsibilities
As a System Software Engineer at NVIDIA, you will:
- Partner with software, research, and product teams to align AI strategies.
- Build and optimize local AI inference stacks for RTX and DGX GPUs.
- Develop runtimes using Llama.cpp, vLLM, PyTorch, WinML, DXCGC, TensorRT‑RTX.
- Optimize AI models with quantization, pruning, sparsity, distillation.
- Perform system‑level debugging, performance optimization, and accuracy trade‑off analysis.
- Establish engineering guidelines for production readiness of new models.
Skills & Qualifications
- Bachelor’s/Master’s/PhD in CS, Software Engineering, Mathematics, or related field.
- 2+ years of professional experience.
- Strong C++ programming and debugging skills.
- Knowledge of data structures, algorithms, machine learning.
- Experience with AI inferencing pipelines using ML/DL frameworks (PyTorch, TensorRT, Llama.cpp, vLLM).
- Interest in runtime internals, scheduling, memory management, KV‑cache, quantization.
- Strong analytical and problem‑solving abilities.
- Excellent communication skills.
Ways to Stand Out
- Contributions to open‑source inference runtimes or performance infrastructure.
- Proficiency in CUDA, GPU programming, Vulkan, DirectX.
- Hands‑on experience with LLM, vision‑language, TTS, ASR, diffusion workloads.
- Track record of delivering end‑to‑end products with distributed teams.
Why Join NVIDIA?
- Work on cutting‑edge AI workloads at scale.
- Exposure to RTX and DGX‑class systems.
- Collaborate with some of the world’s best engineers and researchers.
- Competitive salary and benefits package.
- Inclusive workplace culture with global impact.
Final Thoughts
The NVIDIA System Software Engineer – Local AI role in Pune is an excellent opportunity for engineers passionate about GPU computing, inference runtimes, and edge AI deployment.
With exposure to C++, CUDA, PyTorch, TensorRT, and advanced optimization techniques, this role provides a strong foundation for building high‑performance AI systems that run locally on devices.