AI Compiler and Kernel Intern

What you'll do

• Build AI-agent workflows that interact with code, compilers, GPU kernels, and performance tools.
• Develop tools for agents to collect data, run experiments, and identify optimization opportunities.
• Explore data-driven approaches for compiler optimization, GPU kernel generation, and performance prediction.
• Build reliable interfaces between AI agents and compiler or developer-tool infrastructure.
• Prototype improvements to compiler flows, code generation, and GPU kernels.
• Measure correctness, runtime performance, compile time, and resource utilization on representative workloads.
• Document the design, experiments, results, limitations, and next steps for all projects.

What we're looking for

• Pursuing a BS, MS, or PhD in Computer Science, Computer Engineering, Electrical Engineering, or a similar field.
• Strong programming skills in Python, C, C++, or a similar language.
• Solid foundations in data structures, algorithms, software engineering, and quantitative problem solving.
• Coursework, research, or project experience in AI, machine learning, compilers, GPU kernels, CUDA, or performance engineering.
• Ability to design experiments, analyze results, investigate technical problems, and communicate findings clearly.
• Experience working in AI, compiler, kernel, performance, or systems areas with the ability to learn across technical boundaries.
• Experience building AI agents, LLM applications, evaluation systems, coding workflows, or developer tools (preferred).
• Experience with LLVM, MLIR, CUDA, Triton, reinforcement learning, or high-dimensional data analysis (preferred).