System Software Engineer - Local AI
NVIDIA Corporation (company site, opens in a new tab)4+ yrsPuneOn-siteDirect career pageEst. 30–50 LPA
Posted on 9 Sept
Reach people at NVIDIA Corporation
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at NVIDIA Corporation you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Develop and optimize high-performance local AI inference stacks for RTX, RTX Pro, and DGX GPUs addressing latency, memory efficiency, and scalability.
- Architect and implement modern inference runtimes supporting frameworks like Llama.cpp, vLLM, PyTorch, WinML, DXCGC, and TensorRT for diverse AI workloads including LLMs, vision-language, TTS, ASR, and diffusion.
- Lead end-to-end performance optimizations, system-level debugging, and infrastructure development for performance/accuracy analysis to ensure production readiness of AI models on resource-constrained platforms.
Minimum Requirements
- 4+ years of experience and Bachelor's, Master's, or PhD in Computer Science, Software Engineering, Mathematics, or related field, or equivalent experience.
- Excellent C++ programming and debugging skills, strong understanding of data structures, algorithms, and machine learning.
- Proven experience with AI inferencing pipelines using ML/DL frameworks such as Llama.cpp, vLLM, PyTorch, WinML, DXCGC, and TensorRT.
- Strong knowledge of inference backends and runtime internals including scheduling, memory management, quantization, and hardware-aware optimization.
Ideal Candidate Profile
- Experience contributing to or building open-source AI inference runtimes, model tooling, or performance infrastructure reflecting deep system and GPU programming skills.
- Track record of delivering end-to-end local AI products in multinational, distributed engineering environments.
- Strong proficiency in low-level GPU programming (CUDA), and building high-performance AI systems integrating frameworks like PyTorch, TensorRT, Vulkan, DirectX, and vLLM.