Responsibilities
- work with us for 3 months on developing computational procedures (operators) that can reliably improve a knowledge state over thousands of iterations
- design and testing improvement operators that maintain stability over 1000+ iterations while making genuine progress
- start with simple cases (e.g., shallow refactoring of scientific papers) and demonstrate reliable iteration before scaling to more complex reasoning tasks
Requirements
- experience with LLMs
- good intuitions about what makes reasoning systematic and verifiable
- care about AI transparency
Nice to Have
- strong software engineering background
- concrete examples of how they've applied this background to come up with novel abstractions that push the frontiers of automated reasoning
Work Arrangement
Hybrid
Additional Information
- 3-month contract role
- Potential of full-time offer for exceptional candidates
