AI Compiler Formal Verification Intern

NVIDIA; Zürich; On-site; CHF 120,000 - 180,000; Full time

Job summary

NVIDIA, the leading AI computing company, is seeking a PhD candidate to research and implement formal verification methods for AI compilers, their passes, IRs and sub-graphs, with opportunities to apply semantic verification techniques and static analysis. The role emphasizes pioneering verification for human and agentic-use cases.

Ideal candidates are pursuing a PhD in CS/EE/Math with strong Python or C++ skills and a solid background in formal methods, and may have experience with LEAN or SMT

Qualifications

• Pursuing PhD in Computer Science, Computer/Electrical Engineering, Mathematics or equivalent program.
• Strong Python or C++ programming skills.
• Strong academic background in formal methods (preferably PhD).

Responsibilities

• Research and implement formal methods to verify AI compilers and related passes, IRs and sub-graphs.
• Explore semantic verification techniques to improve AI compiler reliability and safety.

Skills

Python/C++ programming

Formal methods

Education

PhD in CS/EE/Math or equivalent

Tools

LEAN

SMT

Job description

NVIDIA's invention of the GPU 1999 sparked the growth of the PC gaming market, redefined modern computer graphics, and revolutionized parallel computing. More recently, GPU deep learning ignited modern AI — the next era of computing — with the GPU acting as the brain of computers, robots, and self-driving cars that can perceive and understand the world. Today, we are increasingly known as “the AI computing company”.

What you’ll be doing

Research and implement innovative formal methods to verify state of the art AI compilers. This includes but is not limited to AI compiler features, passes, IR's, sub-graphs, lowerings and other critical elements of AI compilers. This role provides you with an opportunity to explore and use AI, formal verification, and other forms of semantic verification or static analysis techniques to innovate solutions that verify AI compilers for human and agentic-use cases.

What we need to see

• Pursuing PhD in Computer Science, Computer/Electrical Engineering, Mathematics or equivalent program
• Strong Python or C++ programming skills
• Strong academic background in formal methods (preferably PhD)

Ways to stand out from the crowd

• Academic or industrial background using LEAN or SMT to solve compiler or compiler-adjacent problems
• Knowledge of deep learning frameworks (such as Pytorch and TensorRT) and compilers

With competitive salaries and a generous benefits package, we are 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 and, due to unprecedented growth, our exclusive engineering teams are rapidly growing. If you're a creative and autonomous engineer with a real passion for technology, we want to hear from you.