Doctoral student in hierarchical reinforcement learning for "AI for Math".
Core
Researching hierarchical reinforcement learning (HRL) to automate theorem provers and generate conjectures/lemmas in interactive theorem provers for the 'AI for Math' initiative.
Role type
Ph.D. researcher in hierarchical reinforcement learning
Builds
Automated proof systems and mathematical conjectures
Domain
AI for Math / Theorem Proving / Hierarchical Reinforcement Learning
Deliverable
production ML models
Required skills
hierarchical reinforcement learning, theoretical computer science, foundational AI/machine learning, mathematics, Python
Preferred skills
logic, theorem provers, interactive proof assistants
Technologies
Python
Responsibilities
Conduct research and aim for publications in top AI venues (NeurIPS, ICML, AAAI), develop scientific concepts, communicate research results, teach undergraduate courses
Seniority
Ph.D. student, research-focused
Sourced via jobtech · Listed on CareerPlan, which tracks 70,000+ jobs from 20+ sources.
