NVIDIA, a pioneer in graphics and accelerated computing for over 25 years, is seeking a seasoned Senior Software Engineer to enhance its AI Infrastructure Solutions team in Pune. This is a premier opportunity to engage with cutting-edge technologies and shape the future of computing.

Join a global innovation leader that fosters a dynamic and inclusive work environment. NVIDIA is committed to diversity and provides equal opportunities. If you are driven by the creation of scalable AI platforms and autonomous agent solutions that transform industries worldwide, we encourage you to connect with us.

This role involves the design, development, and operation of robust AI infrastructure solutions essential for enterprise-level LLM applications and autonomous agents. Key responsibilities include crafting agentic AI workflows and multi-agent systems, leveraging frameworks like LangChain or LangGraph for features such as tool calling, planning, and retrieval-augmented generation (RAG).

You will also be responsible for integrating and serving LLMs via optimized APIs, containerizing applications with Docker, and deploying them on Kubernetes. This includes managing Helm charts, autoscaling, and GPU workloads. A critical aspect is taking applications to L3 support, encompassing production readiness, advanced troubleshooting, root-cause analysis, and performance tuning. Establishing and maintaining system observability through logging, metrics, and tracing for agent behavior and LLM quality is also vital. Building and maintaining CI/CD pipelines for seamless automated deployments and developing high-performance backend services and RESTful APIs using Python and/or .NET Core to expose AI capabilities are core duties.

Candidates should possess a Bachelor’s degree or equivalent experience in Computer Science, Engineering, or a related discipline, coupled with a minimum of 5 years in software engineering. A minimum of 2 years specifically focused on AI/LLM-based solutions is required.

Demonstrated experience in building agentic AI and autonomous agent systems, including tool use, multi-agent orchestration, and RAG pipelines, is essential. Strong proficiency in Python is a must, with experience in C#/.NET Core and ASP.NET Core for REST API development being advantageous. Solid experience with Docker and Kubernetes for production deployment, scaling, and troubleshooting containerized workloads is expected. Proven capability in L3 application support, including incident management, debugging, performance optimization, and root-cause analysis, is crucial. Familiarity with CI/CD tools such as GitHub Actions, Azure DevOps, or Jenkins, and proficiency in Git-based workflows are also necessary.