Empirical
Streams in this track include hands-on research using machine- learning experiments to understand and improve model safety including AI control, interpretability, scalable oversight, evaluations, red-teaming, and robustness. This track is defined by its methods rather than any single research agenda. If your primary tool is ML engineering, this is the track for you.
- Stage 1: Complete the general application
- Stage 2, phase 1: Complete 1–2 assessments evaluating research taste and technical implementation skills, alongside possibly reference requests
- Stage 2, phase 2: Stream selection questions
- Stage 3: Interviews and work-tests
The track is defined by its methodology more than by any single research agenda. Fellows run ML experiments to understand and improve the safety properties of frontier models, with work spanning interpretability, AI control, scalable oversight, evaluations, red-teaming, robustness, and model organisms of misalignment. The unifying thread is that progress comes from hands-on work with real models (training, probing, fine-tuning, measuring, etc.) rather than reasoning from first principles alone. This is the largest track in the program and the most common entry point into technical AI safety research.
We are looking for fellows whose primary tool is ML engineering, broadly construed. The essential requirement is the ability to design and run experiments on language models or other deep learning systems and iterate quickly on the results. In practice, that usually means having a solid understanding of Python (with and without AI coding tools), being comfortable with the infrastructure around running models at moderate scale, and knowing which experiments are worth running. Mission alignment is highly important, and fellows should be able to say why a given line of empirical work meaningfully reduces frontier risk, not just whether it yields a successful publication. Educational background and seniority are weighted lightly here relative to other tracks. Past cohorts have included strong fellows ranging from undergraduates to senior industry researchers.
Fellows are matched to mentors based on fit, and projects are scoped to produce concrete artifacts (i.e., papers, evaluation suites, open-source tooling, or technical reports) by the end of the program. The target audiences for the work produced in this track would include safety and alignment teams at frontier labs, governments and other evaluation organizations, and the broader ML research community.
If you are excited by this kind of work, we encourage you to apply.
Projects in this stream will be on AI welfare and moral status; more specifically, on what it takes to be a moral patient and how we can determine whether AI systems meet the conditions. I'm looking for applicants who have ideas about these topics and are motivated to explore them in more detail.
In this stream we will explore extensions and implications of our discovery that neural networks pretrained on next-token prediction represent belief-state geometry in their activations, decompose their world into parts, and discover abstractions. We will build on this fundamental theory of neural network representations in order to discover the building blocks of cognition.
The Redwood Research stream is looking for fast empirical iterators and strategists to work on control research.
Roger Grosse’s stream investigates how to improve influence functions and other training data attribution methods, and uses these tools to study alignment-related phenomena such as out-of-context reasoning and emergent misalignment. The ideal scholar has experience with LLM internals, strong statistics/applied math skills (especially numerical linear algebra), and can independently drive research from literature review through experimentation and analysis. Roger provides shovel-ready projects while giving exceptional scholars freedom to pursue their own ideas, and is open to scholars collaborating with others.
Backing projects focused on product development and organization building in the areas of AI safety and alignment, biosecurity, and critical cybersecurity. Looking for fellows who are self starters, default to action, and have a desire to create.
This stream will work on projects that empirically assess national security threats of AI misuse (CBRN terrorism and cyberattacks) and improve dangerous capability evaluations. Threat modeling applicants should have a skeptical mindset, enjoy case study work, and be strong written communicators. Eval applicants should be able and excited to help demonstrate concepts like sandbagging elicitation gaps in an AI misuse context.
AIxBio projects on biological data, biological AI models, and their interactions with GPAIs, to directly progress the maturity of interventions and reduce strategic/technical uncertainties. Some projects may be scoped to directly inform Sentinel's AIxBio strategy and resource allocation.
We study when and how AI systems can prove that their outputs are correct, bringing the tools of probabilistic proof systems and complexity theory to bear on AI safety. Our contributions are primarily theoretical, in the form of new definitions, constructions, and techniques, but the work is empirically guided: we run experiments on frontier models and on tiny "fruit-fly" models to test intuitions, and papers often pair a theorem with an experiment.