1 day ago
Pune, IndiaSenior
Responsibilities
- Design, build, and operate AI infrastructure solutions for LLM-based applications and autonomous agents.
- Develop agentic AI workflows and multi-agent systems involving tool calling, planning, memory, retrieval-augmented generation, and orchestration.
- Integrate and serve LLMs through APIs and inference endpoints while optimizing latency, throughput, cost, and reliability.
- Containerize, deploy, and scale applications on Kubernetes using Helm, autoscaling, and GPU-enabled workloads.
- Own L3 production support, including troubleshooting, incident management, root-cause analysis, performance tuning, and escalation support.
- Define observability for AI systems through logging, metrics, tracing, and monitoring of agent behavior, LLM quality, and system health.
- Build and maintain CI/CD pipelines for automated build, testing, and deployment.
- Develop high-performance Python and/or .NET Core backend services and REST APIs exposing AI capabilities.
Requirements
- Bachelor’s degree or equivalent experience in Computer Science, Engineering, or a related field.
- At least 5 years of software engineering experience, including at least 2 years working on AI or LLM-based solutions.
- Hands-on experience building agentic AI and autonomous-agent systems with tool use, multi-agent orchestration, and RAG pipelines.
- Strong experience integrating LLMs through OpenAI-compatible APIs, NVIDIA NIM, Hugging Face, or similar technologies, including prompt engineering and evaluation.
- Strong Python proficiency; C#/.NET Core and ASP.NET Core experience is a plus.
- Production experience with Docker and Kubernetes, including deployment, scaling, and troubleshooting of containerized workloads.
- Experience supporting applications at L3 level, including incident management, debugging, performance optimization, and root-cause analysis.
- Experience with Git-based workflows and CI/CD tools such as GitHub Actions, Azure DevOps, GitLab CI, or Jenkins.
- GPU-accelerated workloads, NVIDIA AI Enterprise, Triton Inference Server, NeMo, MCP, agent-to-agent communication, LLM evaluation, guardrails, safety frameworks, and open-source contributions are advantageous.
Benefits
- NVIDIA offers competitive pay and a comprehensive benefits package.
- The role is based in Pune, or equivalent experience may be considered.
- Employees can access benefits for themselves and their families.
Tech Stack
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.