NVIDIA is seeking a highly motivated and creative Software Engineer Intern to join our SW Infra Team. As an intern, You will play a key role in helping build multi-agent systems and enterprise agent harnesses—the runtime and tooling that enable AI agents to use tools, collaborate, and complete engineering tasks reliably.
This role is ideal for someone interested in turning LLM capabilities into practical software systems. You will work with engineers and researchers to develop agent infrastructure for workflows such as automated regression testing, code review and generation, engineering knowledge retrieval, and Autonomous Vehicle (AV) road event triage.
What You'll Be Doing:
- Design and implement agent harnesses that support tool execution, context and state management, and coordination across multiple agents.
- Build integrations with enterprise tools, code repositories, data platforms, and engineering services to help agents complete real-world development tasks.
- Develop reliable execution capabilities, including sandboxing, access controls, error recovery, and human review and intervention.
- Build evaluation and observability tools to measure agent task success, trace execution, replay trajectories, and improve performance, latency, and cost.
- Collaborate with engineers to prototype agent workflows, validate them against realistic tasks, and improve them through experimentation and feedback.
What We Need to See:
- Currently pursuing a master’s, or PhD in Computer Science, Electrical Engineering, or a related field.
- Programming experience in at least one language, such as Python, C, C++, Rust, or TypeScript, and an understanding of software engineering fundamentals, including data structures, APIs, testing, and debugging.
- Basic familiarity with LLM APIs and an interest in agent systems. Exposure to concepts such as prompting, agent loops, skills, subagents, Model Context Protocol (MCP), tool use, or agent memory through coursework or personal projects is a plus.
- Hands-on software development experience through coursework, research, internships, open-source contributions, or personal projects.
- Interest in multi-agent systems, with the ability to investigate problems, experiment, and communicate technical findings clearly.
- Regular use of agentic coding tools such as Codex, Claude Code, Cursor, or similar products, with curiosity about how they work and an interest in exploring their underlying implementation.
Ways to Stand Out from the crowd:
- Experience building an agent harness or multi-agent application, including task delegation, shared state, memory, or coordination between agents.
- Experience testing an agent on sample tasks and comparing results to identify improvements.
- Basic familiarity with Linux, Git, containers, or cloud platforms.
- Interest in secure agent execution, including permissions, sandboxing, and human review.
- Open-source contributions or small projects using AI agents to automate coding, testing, or data analysis.
Widely considered to be one of the technology world’s most desirable employers, NVIDIA offers highly competitive salaries and a comprehensive benefits package. As you plan your future, see what we can offer to you and your family www.nvidiabenefits.com/
#deeplearning