NVIDIA Logo

NVIDIA

Senior System Software Engineer

Posted 4 Days Ago
Be an Early Applicant
In-Office
Pune, Maharashtra, IND
Senior level
In-Office
Pune, Maharashtra, IND
Senior level
Design and develop low-latency, GPU-accelerated video streaming features; optimize encoder and GPU/CPU pipeline performance; build video quality measurement and analysis tools; integrate AI models for real-time video processing and adaptive streaming; and improve reliability, telemetry, and debugging for cloud-based streaming systems.
The summary above was generated by AI

NVIDIA's GeForce NOW, the next-generation gaming service powered by NVIDIA GPUs in the cloud, transforms a Mac, PC, or mobile device into a high-performance gaming machine. GeForce NOW keeps games up-to-date automatically, enabling users worldwide to instantly stream the latest games in high-definition resolution with minimal latency and the smoothest gameplay. Just click and play! Visit us at https://www.nvidia.com/en-us/geforce-now. We are now extending this industry defining technology to a new range of applications including virtual and augmented reality, artificial intelligence and remote controlled robotics.

We are seeking a Senior Software Engineer to join a team of skilled and motivated engineers who develop a high performance, low latency streaming stack that delivers unprecedented video quality at lowest latency that makes gaming from the cloud the preferred gaming platform for millions.

What you will be doing:
  • Design and develop new video streaming functionalities delivering new interactive experiences

  • Innovate, design and develop features to improve image quality, performance, reliability, security and maintainability

  • Analyze GPU/ CPU performance for the video pipeline, isolate bottlenecks and implement solutions in collaboration with GPU hardware and software teams to deliver top performance

  • Develop tools to measure video quality experienced by users, refine to enable evaluation of quality improvements with high confidence

  • Leverage features and toolsets in latest video compression technologies to deliver high quality streaming solutions tailored for different interactive graphics applications

  • Develop quality-evaluation and analysis capabilities that use metrics along with encoder statistics to detect regressions, evaluate new video features, and guide codec and pipeline tuning.

  • Apply machine learning and AI models to develop specialized video processing and adaptive streaming algorithms to minimize perceptible artifacts while delivering the lowest latency under different network conditions.

What we need to see:
  • 5 + years of experience with Bachelor's or Master's degree in Computer Science or a related area.

  • Proficiency in C, C++, Python

  • Strong understanding of real-time GPU-accelerated video pipeline performance, including encoder behavior, color spaces, video scaling, transport efficiency, buffering, pacing, bitrate adaptation, frame handling, and latency-sensitive optimizations in distributed or cloud-based systems.

  • Familiarity with API frameworks such as Vulkan, CUDA, OpenGL and DX

  • Solid understanding of toolsets in different video codecs like H.264, HEVC, and AV1, including tuning codec configurations to meet application requirements and trade-offs.

  • Experience debugging and improving reliability and stability in complex streaming systems, including issues related to degraded network conditions, packet loss recovery, telemetry, tracing, field validation, and long-running session behavior.

  • Proficiency in telemetry, statistical data analysis, and performance monitoring to measure and optimize video quality, latency, and system performance in cloud infrastructures.

  • Experience in using and integrating AI models into real-time video pipelines

  • Experience with objective video quality assessment using metrics such as VMAF, CAMBI, PSNR, and SSIM/MS-SSIM, and the ability to correlate those metrics with perceptual video quality across different content types and artifacts.

  • Strong understanding of different layers of software stack including OS internals, user-mode and kernel-mode drivers, strong system software performance analysis, testing and debugging skills

Ways to stand out from the crowd:
  • Experience in optimizing video pipelines on multiple GPU families such as Intel integrated and AMD GPUs

  • Experience writing or analyzing graphics rendering applications or advanced AI based graphics generation such as DLSS, RTX, FSR

At NVIDIA, we’re committed to diversity, equity, and inclusion. We embrace diverse perspectives and are proud to be an equal opportunity employer.

NVIDIA Pune, Mahārāshtra, IND Office

Survey No.144 145, Commerzone No.5, Off, Airport Rd, Yerawada, Pune, Maharashtra, India, 411006

Similar Jobs

Yesterday
In-Office
Pune, Maharashtra, IND
Senior level
Senior level
Artificial Intelligence • Computer Vision • Hardware • Robotics • Metaverse
Design, implement, and maintain infrastructure and CI/CD pipelines to deploy and automate local AI workloads across inference backends. Build model download and repository sync systems, implement data processing and visualizations, measure accuracy and performance, debug existing frameworks, and collaborate with developers to streamline debugging and deployment of AI applications and models.
Top Skills: C#DockerGitGrafanaJavaJenkinsKibanaKubernetesLlama.CppOllamaPerforcePerlPHPPythonPyTorchSQLTrt-RtxWinml
2 Days Ago
In-Office
Pune, Maharashtra, IND
Senior level
Senior level
Artificial Intelligence • Computer Vision • Hardware • Robotics • Metaverse
Design and optimize on-device AI inference stacks for RTX and DGX systems. Build inference runtimes, optimize models and pipelines (quantization, pruning), perform system-level debugging and performance-accuracy tradeoffs, and collaborate across software, research, architecture, and product teams to ensure production readiness.
Top Skills: C++CudaDgxDirectxDxcgcLlama.CppPyTorchRtxTensorrtVllmVulkanWinml
2 Days Ago
In-Office
Pune, Maharashtra, IND
Senior level
Senior level
Artificial Intelligence • Computer Vision • Hardware • Robotics • Metaverse
Develop and optimize on-device AI inference stacks and runtimes for RTX and DGX systems. Collaborate with cross-functional teams to design high-performance, memory-efficient inference pipelines, apply model optimizations (quantization, pruning, distillation), perform system-level debugging and performance tuning, and build infrastructure for performance/accuracy evaluation and production readiness.
Top Skills: C++CudaDgxDirectxDxcgcLlama.CppPyTorchRtxTensorrtTensorrt-RtxVllmVulkanWindows Ml

What you need to know about the Pune Tech Scene

Once a far-out concept, AI is now a tangible force reshaping industries and economies worldwide. While its adoption will automate some roles, AI has created more jobs than it has displaced, with an expected 97 million new roles to be created in the coming years. This is especially true in cities like Pune, which is emerging as a hub for companies eager to leverage this technology to develop solutions that simplify and improve lives in sectors such as education, healthcare, finance, e-commerce and more.

Sign up now Access later

Create Free Account

Please log in or sign up to report this job.

Create Free Account