3 days ago
Pune, IndiaSenior
Responsibilities
- Design, implement, and maintain system software and infrastructure for AI workloads across multiple inference backends.
- Define deployment requirements and develop automation to measure correctness, functionality, reliability, and system performance.
- Build infrastructure for downloading, managing, and synchronizing local AI model repositories.
- Analyze datasets and workload metrics, develop data-processing infrastructure, and create visualizations for developers.
- Implement system instrumentation, diagnostics, and debugging capabilities in collaboration with Local AI developers.
- Maintain automated build, integration, deployment, and qualification infrastructure across inference frameworks and environments.
- Debug existing frameworks, identify performance bottlenecks, and improve system efficiency and scalability.
Requirements
- 5+ years of experience and a B.Tech or higher degree in Computer Science, Information Technology, Software Engineering, or a related field.
- 5+ years of software development experience with strong programming skills in C/C++, C#, Java, or another systems programming language.
- Experience with at least one scripting language such as Python.
- Experience with system APIs, multithreaded software, process and resource management, debugging, or performance analysis.
- Familiarity with databases, SQL, source control systems, and CI/CD infrastructure such as Git, Perforce, and Jenkins.
- Strong analytical, systems debugging, problem-solving, multitasking, written communication, and oral communication skills.
- Preferred experience with system software, runtime infrastructure, scalable backend components, profiling, performance optimization, telemetry, observability, Linux/Windows system programming, Kubernetes, Docker, Grafana, Kibana, and AI inference frameworks.
- Preferred understanding of CPU/GPU utilization, memory management, concurrency, and AI workload performance characteristics.
- Preferred experience analyzing Nsight Systems traces and integrating or debugging Llama.cpp, Ollama, PyTorch, vLLM, WinML, or TRT-RTX.
Benefits
- Competitive salaries and a generous benefits package.
- Equal-opportunity employer committed to 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.