Work With Top
Talent on AI Safety

Open Position:
AI Safety Research Engineer

This position involves working with Max Tegmark and Steve Omohundro on provable AI safety via formal verification, as described here (a high-level introduction is given in the 2nd half of this TED talk).  The position can be either remote or at MIT in Cambridge, Massachusetts.

The ideal candidate:

  • Want to ensure that powerful AI systems stay under human control

  • Concerned that AGI is not many decades away,  and that current AI safety approaches may be inadequate for such a transformative technology

  • Significant experience in formal verification or mathematical theorem proving, ideally with PhD or extensive work in the field

  • Strong programmer

  • Likes mathematics and machine learning

  • Self-motivated and enjoys working fairly independently

Annual compensation:

$70,000—$180,000 USD depending on experience

Open Position:
Software Engineer

This position involves working with Bryan Parno, Max Tegmark and colleagues at the Beneficial AI Foundation on turbocharging formal verification of Rust code with AI tools as described here and in Towards Guaranteed Safe AI (a high-level introduction is given in the 2nd half of this TED talk). The ideal candidate:

  • Strong software engineering background

  • Very strong at Rust programming

  • "Verification curious": eager to learn about formal verification techniques for making provably bug-free code

  • Self-motivated, comfortable working independently and collaboratively with academic and research partners

  • Eager to contributed to free open-source tools ensuring that code does what we want it to do

Annual compensation:

$70,000—$150,000 USD depending on experience and qualifications