3 days ago
Beijing, ChinaIntern
Responsibilities
- Identify bottlenecks in software development workflows, form testable hypotheses, and build prototypes that demonstrate measurable improvements in developer efficiency.
- Design and implement AI-agent capabilities for code generation, debugging, testing, knowledge retrieval, workflow automation, and long-running development tasks.
- Collaborate with software engineers, AI researchers, and infrastructure teams to integrate agent-based solutions into NVIDIA development environments.
- Evaluate agent systems through reproducible experiments covering reliability, accuracy, latency, resource usage, and generated-code quality.
- Turn successful experiments into robust, maintainable Python software for broader engineering teams.
Requirements
- Currently pursuing a Bachelor's, Master's, or PhD degree in Computer Science, Software Engineering, or a related field.
- Strong programming and software engineering skills, particularly proficiency in Python and the ability to write clean, testable, and maintainable code.
- Understanding of operating systems, computer networks, storage systems, concurrency, and distributed systems.
- Strong self-motivation and problem-solving ability, including the ability to discover meaningful problems, work independently, and validate ideas through rapid experimentation.
- Good written and spoken English communication skills for explaining technical ideas and collaborating in an international engineering environment.
- Hands-on experience with AI-assisted development tools such as Claude Code, Codex, Cursor, or similar coding agents.
- Preferred experience building AI agents, coding assistants, autonomous development workflows, or developer productivity tools.
- Preferred familiarity with agent frameworks and open-source projects such as Hermes, DeepSeek Harness, memory systems, or comparable agent runtimes and orchestration frameworks.
- Preferred experience evaluating large language model applications, including prompt design, tool use, context management, memory, benchmarking, and reliability testing.
- Open-source contributions, technically ambitious personal projects, or examples of independently identifying and solving real developer problems are desirable.
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.