PhD Studentship: Causal Reinforcement Learning

• Conduct foundational research at the intersection of causal inference and reinforcement learning, formalizing policy learning from biased datasets and developing algorithms that leverage causal structure for robust generalization.
• Build and evaluate RL algorithms that integrate causal reasoning to improve out-of-distribution performance and provide policy guarantees.
• Benchmark proposed methods on controlled simulated environments with known causal structure against standard and offline RL baselines.

This research aims to make AI control systems more robust and generalizable, enabling safer and more efficient automation of industrial infrastructure, which can reduce energy consumption and improve sustainability.

• First-class or upper second-class honours degree (or equivalent) in Computer Science, Mathematics, Engineering, Statistics, or a related technical field.
• Strong background in at least one of: reinforcement learning, machine learning, probabilistic modelling, or control theory.
• Proficiency in Python and standard ML libraries (PyTorch, NumPy, SciPy, scikit-learn).
• Clear scientific writing skills and ability to communicate research to both academic and applied audiences.

Fully funded 4-year PhD studentship co-funded by Phaidra and administered by the University of Cambridge. Benefits include competitive compensation, meaningful equity, unlimited PTO with 20-day minimum, paid parental leave, medical/dental/vision insurance, flexible stipends, and a company MacBook. Remote-first culture with asynchronous communication.

Phaidra builds AI-powered control systems for industrial facilities using reinforcement learning to automatically learn and improve over time, reducing energy use and optimizing performance.