ML Research Resident
This job is no longer available
There are still lots of open positions. Let's find the one that's right for you.
About The Position
Elicit is building a research agent that can use an unlimited amount of test-time compute while keeping its reasoning transparent and verifiable. As a research resident, you'll work with us for 3 months on developing computational procedures (operators) that can reliably improve a knowledge state over thousands of iterations. A knowledge state consists of structured information - for example, a scientific paper might be represented as a set of claims supported by evidence and connected through logical reasoning; this might be combined with scratchpads, evergreen “notes to self”, search trees, and other information. The goal is to make genuine progress in understanding - separating inferences from raw evidence, finding connections between ideas, building clearer explanations, and identifying gaps in reasoning. Improvements should be epistemically sound, making the knowledge state more useful while remaining human-readable. An improvement might reorganize information to better answer a question, find an implicit assumption in an argument, or connect evidence across multiple sources. Your work will focus on designing and testing improvement operators that maintain stability over 1000+ iterations while making genuine progress, starting with simple cases and scaling to more complex reasoning tasks. Developing systems that perform legible reasoning over long horizons addresses core challenges in AI transparency and scalable reasoning.
