PhD Studentship: Causal Reinforcement Learning

1 month, 1 week ago
Internship
Entry Level
Artificial Intelligence and Machine Learning
Phaidra

Phaidra

Phaidra is an industrial AI company that creates self-learning, intelligent control systems for industrial facilities. By leveraging AI technology, Phaidra helps operators reduce risk, improve energy efficiency, and meet sustainability goals by maximiz...

Internet Software & Services
51-250
Founded 2019
$30M raised

Description

  • Develop theoretical foundations for policy learning from biased, small datasets through a causal lens.
  • Characterize how confounding and mediators affect offline reinforcement learning.
  • Build RL algorithms that use known or learned causal structure to improve out-of-distribution generalization and provide policy guarantees.
  • Design and evaluate methods in controlled simulated environments with known causal structure.
  • Benchmark proposed approaches against standard and offline RL baselines.
  • Contribute to foundational RL research while staying grounded in real-world industrial challenges.
  • Work under the supervision of academic and industrial co-supervisors at Cambridge and Phaidra.

Requirements

  • A 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 including PyTorch, NumPy, SciPy, and scikit-learn.
  • Clear scientific writing skills and the ability to communicate research to academic and applied audiences.
  • Eligibility to study at the University of Cambridge; international students are welcome and English language requirements apply.
  • Familiarity with causal inference, causal graphical models, or structural equation models (preferred).
  • Prior research experience such as an undergraduate thesis, MSc dissertation, research internship, or publications (preferred).
  • Experience with offline RL, batch RL, or safe RL (preferred).
  • Exposure to applying ML to real-world physical or industrial systems (preferred).

Benefits

  • Fully funded 4-year PhD studentship.
  • Expected start date in January 2027.
  • 100% remote company with no physical office.
  • Competitive compensation with meaningful equity.
  • Medical, dental, and vision insurance (varies by region).
  • Unlimited paid time off with a required minimum of 20 days per year.
  • Paid parental leave (varies by region).
  • Flexible stipends for workspace, well-being, and professional development.

Interested in this position?

Apply directly on the company website

Apply Now

Similar Roles

Senior Research Engineer, Threat Intelligence

SecurityScorecard 251-1K IT Services

SecurityScorecard is hiring an engineering-focused Threat Intelligence team member to turn research findings into production-ready detections, feeds, and platform capabilities for STRIKE.

AWS CI/CD Cybersecurity Go Node.js Python Splunk SQL TypeScript
1 week, 2 days ago

Engineering Lead, Inference Optimization

Venice AI is hiring an Inference Optimization leader to drive technical strategy and scale privacy-focused LLM inference performance across its GPU infrastructure.

C++ Go Python Rust
1 week, 4 days ago

Senior Scientific Platform Engineer

VivoSense 11-50 Professional Services

VivoSense is hiring a Senior Scientific Platform Engineer to transform scientific and digital health workflows into scalable, production-ready platform capabilities for clinical studies and customer deliverables.

AWS C# CI/CD .NET Python R Serverless
1 week, 4 days ago

Associate Research Scientist, Real World Evidence

Precision AQ 1001-5000 Business Consulting and Services

Precision AQ is hiring a fully remote Associate Research Scientist on its Real-World Evidence team to support real-world studies in the pharmaceutical and biotech space.

Python R SQL
1 week, 6 days ago

You're on a roll! Sign up now to keep applying.

Sign Up

Already have an account? Log in

Used by 14,729+ remote workers