Summary
Elicit is building a research agent focused on improving reasoning transparency and verifiability in AI. As an ML Research Resident, you will develop computational procedures to enhance knowledge states over thousands of iterations, ensuring that improvements are systematic and epistemically sound.
Responsibilities
- Develop computational procedures (operators) that can reliably improve a knowledge state over thousands of iterations
- Design and test improvement operators that maintain stability over 1000+ iterations while making genuine progress
- Start with simple cases and demonstrate reliable iteration before scaling to more complex reasoning tasks
Skills
- Experience with LLMs
- Good intuitions about what makes reasoning systematic and verifiable
- Care about AI transparency
- Strong software engineering background
- Concrete examples of how they've applied their software engineering background to come up with novel abstractions that push the frontiers of automated reasoning
Qualifications
Must Haves
- Experience with LLMs
- Good intuitions about what makes reasoning systematic and verifiable
- Care about AI transparency
Nice to Haves
- Strong software engineering background
- Concrete examples of how they've applied their software engineering background to come up with novel abstractions that push the frontiers of automated reasoning