Senior Software Engineer, AI Apps and Frameworks

We are looking for a skilled Agentic AI Software Engineer to join our team. The ideal candidate is passionate about building autonomous, multi-agent systems and will be responsible for designing, developing, and maintaining integrations of NVIDIA NIM microservices and Blueprints into leading agentic AI frameworks and open-source libraries. You will work across the agentic AI ecosystem to enable Day-0 NVIDIA model and inference support in agent orchestration platforms and tooling.

What you'll be doing:

• Design and implement NVIDIA NIM connectors and Blueprint integrations into upstream agentic AI frameworks (e.g., LangGraph, LlamaIndex, AutoGen, CrewAI, Claude Agent SDK, OpenAI Agents SDK)

• Build and maintain agentic workflows — including tool use, memory, planning, and multi-agent coordination patterns — powered by NVIDIA inference services

• Develop test harnesses and evaluation pipelines to validate agent behavior, tool-call correctness, and end-to-end workflow quality

• Evangelize NVIDIA agentic AI capabilities through demos, documentation, and upstream community contributions

• Partner with NVIDIA NIM and release teams to ensure Day-0 agentic support for new models and inference APIs

• Continuously discover emerging agentic frameworks and drive integrations that expand the NVIDIA agentic ecosystem

• Mentor junior engineers and review contributions from internal and external contributors

What we need to see:

• Bachelor's or Master's degree in Computer Science or a related field, or equivalent experience

• 8+ years of experience in software design, development, and testing

• Hands-on experience building with LLM-based agent frameworks and patterns (tool use, RAG, multi-agent orchestration, structured outputs)

• Familiarity with inference APIs and serving frameworks (OpenAI-compatible APIs, NIM, vLLM, TensorRT-LLM)

• Experience in open-source development — contributing to and maintaining upstream projects

• Strong understanding of AI application developer workflows and the modern agentic AI stack

• Strong verbal and written communication skills

• Action-driven with strong analytical and debugging skills

• Ability to adapt quickly in a fast-moving, research-driven environment

• Enthusiasm for working across multiple diverse projects and communities

Ways to stand out from the crowd:

• Demonstrated contributions to agentic AI frameworks or LLM orchestration libraries

• Experience designing and evaluating multi-agent systems, including reliability, latency, and correctness at scale

• Deep familiarity with the open-source inference and agentic ecosystem (LangChain, LlamaIndex, AutoGen, Haystack, etc.)

• Published work, blog posts, or conference talks on agentic AI or LLM systems

With a competitive salary package and benefits, NVIDIA is widely considered to be one of the technology world’s most desirable employers. We have some of the most forward-thinking and hardworking people in the world working for us. Are you a creative and autonomous Systems Software Engineer, who loves challenges? Do you have a genuine passion for advancing the state of 3D computer vision across a variety of industries? If so, we want to hear from you.

Your base salary will be determined based on your location, experience, and the pay of employees in similar positions. The base salary range is 184,000 USD - 287,500 USD.

You will also be eligible for equity and benefits.

Applications for this job will be accepted at least until May 12, 2026.

This posting is for an existing vacancy. 

NVIDIA uses AI tools in its recruiting processes.

NVIDIA is committed to fostering a diverse work environment and proud to be an equal opportunity employer. As we highly value diversity in our current and future employees, we do not discriminate (including in our hiring and promotion practices) on the basis of race, religion, color, national origin, gender, gender expression, sexual orientation, age, marital status, veteran status, disability status or any other characteristic protected by law.