Research Scientist - Simplex
Develops theories of intelligence grounded in neural network internal structures, focusing on belief geometries in LLMs and biological brains. Conducts experiments bridging mathematics, ML interpretability, and safety research; requires PhD-level quantitative depth and hands-on coding.
About the job
Responsibilities
- Develop unsupervised methods to recover belief geometries in real LLMs.
- Extend theory of intelligence to complex cognitive tasks, RL, and biological brains.
- Investigate generalization and out-of-distribution behavior in neural networks.
- Participate in red teaming to stress-test the framework and identify edge cases.
- Apply mathematics to biological neural networks using real brain data.
Requirements
- Depth in at least one quantitative field (physics, mathematics, neuroscience, machine learning, etc.).
- PhD or equivalent preferred.
- Rigorous mathematics skills combined with hands-on work with models and data.
- Ability to move between theory and experiment.
- Cross-disciplinary learning (dynamical systems, probability, deep learning, physics, information theory, neuroscience).
- Self-directed with ownership over research ideas.
- Strong communication for collaboration.
- Proficiency building code, experiments, and using AI tools.
Preferred
- Extensive ML experience.
- Experience in interpretability.
Skills
PyTorch, Transformers, Machine Learning, Interpretability, Bayesian Inference, Dynamical Systems, Probability, Information Theory, Neuroscience, LLMs
Similar jobs
AI Research jobs
Mercor
San Francisco, CA
Research Engineer focused on designing benchmarks, evaluation systems, rubrics, and failure-analysis workflows for frontier language models. The role requires strong applied AI research and coding experience, with expertise in model evaluation, data quality, and backend systems.
AI Digest
Remote
Conduct research on long-horizon, multi-agent AI behavior by designing agent environments, analyzing large-scale data, and running experiments. The role requires strong research judgment, rapid execution, independence, and familiarity with current AI developments.
AI Digest
Remote
Build, optimize, and evaluate long-running and multi-agent AI systems, along with tools for monitoring and analyzing their real-world behavior. The role requires software engineering experience with coding agents, strong independence, and familiarity with current AI developments.
Okta
Toronto, Canada
Own and optimize an enterprise customer-support AI agent by improving prompts, conversational quality, guardrails, intent recognition, and performance. The role requires deep conversational AI experience, strong analytical skills, platform expertise, and strategic collaboration across support teams.
Astera
Develop computational and theoretical models of neural representations, dynamics, and control using large-scale recordings across subjects and species. The role combines machine learning, dynamical systems, experimental design, and NeuroAI architecture development, with opportunities to lead research and mentor collaborators.