21 hours ago
Pune, India or Bengaluru, IndiaSenior
Responsibilities
- Design and develop accelerated microservices and libraries.
- Build and maintain real-time vision-language model inference microservices spanning video ingestion, preprocessing, model serving, and downstream integration.
- Collaborate with engineering and Product Management teams to translate requirements into milestone deliverables.
- Develop automated functional, accuracy, and performance regression tests.
- Own component readiness through integration, release, and post-release debugging.
- Profile and optimize latency, throughput, GPU memory usage, and concurrent user capacity across platforms.
Requirements
- Bachelor’s or master’s degree in Computer Science or a related engineering field.
- 8+ years of software development experience.
- Strong software design and programming skills in C/C++ and Python.
- Hands-on experience building microservices using containers, REST APIs, and asynchronous messaging.
- Hands-on experience integrating and serving computer vision and vision-language models in production.
- Understanding of real-time video processing and tradeoffs among latency, throughput, and resource utilization.
- Strong debugging skills and experience diagnosing model quality, accuracy, and performance regressions.
- Preferred experience delivering end-to-end video AI applications using RTSP and FFmpeg.
- Preferred background with NVIDIA DeepStream, TensorRT, Triton Inference Server, CUDA, or comparable technologies.
- Preferred experience optimizing GPU inference pipelines, including batching, memory management, concurrent model execution, KV-cache management, quantization, and stateful streaming inference.
- Preferred experience using NVIDIA Nsight Systems and deploying inference services across x86 and ARM platforms.
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.