Senior System Software Engineer – Accelerated Microservices and Libraries at Nvidia, Pune
Open. Posted .
Real-time vision-language inference services span video ingestion, model serving, downstream integrations, automated regression tests, and GPU performance optimization. The role is based in Pune.
Applying opens the employer's page. Want jobs like this sent to you each morning? Open Elip.
| Location | Pune, Maharashtra |
|---|---|
| Work mode | On-site |
| Experience | 8–9 years |
| Pay | Not stated by the employer |
| Role | AI Engineer |
| Skills asked for | C/C++, Python, Microservices, REST APIs, Asynchronous messaging, Computer vision, Vision-language models, Real-time video processing |
| Posted | 3 Nov 2026 |
Elip's summary
Builds accelerated microservices and libraries for a semiconductor and computing technology company. Develops real-time vision-language model inference services, integrating computer vision models and optimizing video processing, model serving, latency, and GPU utilization with C/C++ and Python. Applies REST APIs and asynchronous messaging to deliver production inference systems.
The job, in the employer's words
We are looking for a senior software engineer to contribute to building accelerated microservices and libraries for our harnesses and agents. In this role, you will be part of an engineering team designing and developing microservices and libraries and optimizing these for relevant metrics.
What you will be doing:
Contribute to design and development of accelerated microservices and libraries
Collaborate with peer engineering and Product Management teams to understand requirements and translate these into deliverables across milestones.
Design, develop, and maintain real-time vision-language model inference microservices, from video ingestion and preprocessing through model serving and downstream integration.
Develop automated functional, accuracy, and performance regression tests, and own component readiness through integration, release, and post-release debugging.
Profile and optimize end-to-end latency, throughput, GPU memory usage, and concurrent user capacity across platforms.
What we need to see:
Masters or Bachelors degree in Computer Science, or related engineering field
8+ years of overall experience in software development , a strong technical foundation in software design principles and strong 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 the tradeoffs among latency, throughput, and resource utilization and strong debugging skills.
Experience evaluating model quality and diagnosing accuracy or performance regressions across model, preprocessing, and inference-runtime changes.
Ways to stand out from the crowd:
Experience delivering end-to-end video AI applications, including video ingestion, inference, tracking, analytics, and downstream integrations, using technologies such as RTSP and FFmpeg.
Background with NVIDIA DeepStream, TensorRT, Triton Inference Server, CUDA, or comparable technologies.
Experience optimizing and profiling GPU inference pipelines, including batching, memory management, and concurrent model execution.
Experience with stateful streaming inference, KV-cache management, batching, quantization, and their impact on serving performance.
Experience profiling GPU applications with tools such as NVIDIA Nsight Systems and deploying inference services across x86 and ARM platforms.
NVIDIA is widely considered to be one of the technology world’s most desirable employers. We have some of the most forward-thinking and passionate people in the world working for us. Are you a creative problem solver with a passion for solving real-world problems with AI? If so, we want to hear from you.
About Nvidia
Headquartered in Santa Clara, founded in 1993.
- People in Elip's index who work here
- 56,179
- Typical time at Nvidia
- 3.9 years
- Typical career length so far
- 13.3 years
Largest teams
- Engineering24,591 people
- Information Technology3,955 people
- Operations2,417 people
- Research2,026 people
Where people here worked before
- Intel3,100 people
- Mellanox Technologies1,320 people
- Qualcomm1,049 people
- Google881 people
- AMD866 people
Where people went next, since 2025
- Google180 people
- Meta172 people
- Apple114 people
- AMD78 people
- Amazon76 people
Totals from public professional profiles in Elip's index; any group under ten people is left out.
Similar open jobs
About this page
Elip lists jobs that employers publish on their own careers sites, never copies from job boards. This one comes from Nvidia's listing on Workday, posted 3 Nov 2026. The summary is Elip's; the description is the employer's. When the job closes, this page says so.