PhD Studentship: Causal Reinforcement Learning

Phaidra
Cambridge
Workplace: RemoteFull timeFunction: Education & TrainingSkills: ["Scientific writing","Communication"]

Develop foundational research that makes reinforcement learning more robust and generalizable by integrating causal reasoning into sequential decision-making. You’ll work with an academic supervisor at the University of Cambridge and industrial co-supervisors at Phaidra, progressing from theory (offline RL, confounding/mediators) to algorithm development (causal structure, out-of-distribution generalization, policy guarantees) and benchmarking on controlled simulated environments.

Loading

Loading job details...

Preparing the role view and application actions.

FursaFursa
Phaidra
Phaidra
1 month ago

PhD Studentship: Causal Reinforcement Learning

✓ Verified Job

Canonical indexed version, validated from employer's careers page.

Source: Company careers pageValidated by: Fursa AI
Last checked: 7 hours agoStatus: Live

Job Summary

Develop foundational research that makes reinforcement learning more robust and generalizable by integrating causal reasoning into sequential decision-making. You’ll work with an academic supervisor at the University of Cambridge and industrial co-supervisors at Phaidra, progressing from theory (offline RL, confounding/mediators) to algorithm development (causal structure, out-of-distribution generalization, policy guarantees) and benchmarking on controlled simulated environments.
Location: Cambridge
Workplace: Remote
Employment Type: Full time · 48 months
Job Function: Education & Training
Seniority: Graduate level

Key Responsibilities

  • •Conduct causal-RL research addressing robustness and generalization failures caused by spurious correlations in RL deployments.
  • •Formalize policy learning from biased, small datasets through a causal lens, including confounding and mediators in offline RL.
  • •Develop RL algorithms that leverage known or learned causal structure to improve out-of-distribution generalization and provide policy guarantees.
  • •Benchmark and evaluate proposed methods on controlled simulated environments with known causal structure against standard and offline RL baselines.
  • •Collaborate with supervisors at the University of Cambridge and Phaidra, contributing to both academic literature and practical deployment considerations.

Pay and Benefits

Equity and Bonus:Equity
Perks:Remote WorkHealth InsuranceDentalVisionPaid LeaveMedicalCompany Macbook

Key Requirements

  • •First-class or upper second-class honours (or equivalent) in Computer Science, Mathematics, Engineering, Statistics, or a related technical field.
  • •Strong background in 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 academic and applied audiences.
  • •Eligibility to study at the University of Cambridge (international students welcome; English language requirements apply).
Education:University of Cambridge
Skills:Scientific writingCommunication
Languages:English
Tech Stack:PythonPyTorchNumPySciPyScikit-learn

Eligibility

Work Authorization:Authorization required. Sponsorship not provided.

Company Brief

Phaidra
Develops AI-driven solutions and tooling to help organizations build, deploy, and manage conversational agents and intelligent assistants, combining large language models with data connectors and orchestration for enterprise use cases.
Industry: AI & Machine Learning
Website