We’re building products to make the future of software correct, understandable, and secure. Right now, AI has raised the floor on software engineering. We’re building for the world where it raises the ceiling.
Our approach is to write software correctness feedback that scales with complexity and volume of code, so software is provably safe and reliable.
What this looks like in practice:
Post-training that make models as good at program analysis and formal reasoning as they are at writing Python.
Interfaces for navigating complex implementations of simple specifications to help users find bugs, generate design documentation, and implement non-functional requirements using compiler-level reasoning methods.
We’re a team of researcher-builders who prioritize impact. We’ve developed cryptography which secures trillions of daily internet connections, helped nonprofits raise tens of millions of dollars, and built experimental educational programs serving hundreds of students.
We’ve worked at leading companies like Jane Street, Google, and Microsoft, and have published research at top venues like NeurIPS, ICML, POPL, and ITP.
We’re hiring engineers and researchers who want to work across AI, programming languages, and security.
Open roles:
If this sounds exciting to you, apply here.