Ruibo T
Machine Learning Engineer at Qlik
Stockholm, Stockholm County, Sweden
Summary
👤
Senior🎓
Top SchoolRuibo T is a machine learning engineer and former postdoc based in Stockholm with nine years' experience building AI systems for tabular data and time series, now developing production-facing solutions at Qlik. He holds a PhD in causality and machine learning from KTH, where his research spanned causal discovery, missing-data methods, fairness, and foundation models for tabular domains. Ruibo has blended academic depth with industry experience—internships and visiting roles at AWS and Microsoft informed practical evaluation and fairness work, and he has contributed to the widely used py-why/causal-learn library by improving mvPC support and tests for missingness-aware causal inference. Comfortable with deep generative models (diffusion) and Tabular LLMs, he brings both research rigor and hands-on algorithm implementation to real-world data challenges. A less obvious strength is his focus on bridging missing-data assumptions with causal methods, making his models more robust in messy production settings.
9 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD, Causality and machine learning, Doctor of Philosophy - PhD, Causality and machine learning at KTH Royal Institute of TechnologyBachelor's degree, Electrical, Electronics and Communications Engineering, Bachelor's degree, Electrical, Electronics and Communications Engineering at Dalian University of Technology
Chinese, English
Github Skills (6)
statistics10
causal-discovery10
python10
causal-inference10
testing9
numpy8
Programming languages (3)
Github contributions (5)
py-why/causal-learn
Feb 2022 - Jun 2022
Causal Discovery in Python. It also includes (conditional) independence tests and score functions.
Role in this project:
Data Scientist
Data ScientistContributions:7 commits, 5 PRs, 1 comment in 3 months
Contributions summary:Ruibo primarily contributed to implementing and testing causal discovery algorithms within the `causal-learn` repository. Their work involved modifying the `PC.py` file to enable the use of background knowledge in the missing value Peter-Clark (mvpc) algorithm, which is crucial for causal inference in real-world scenarios. Furthermore, they added tests for the `get_parent_missingness_pairs()` function and performed modifications to existing tests to improve the reliability of independence tests using mv_fisherz.
continouspythontranslationcausaltetrad
TURuibo/Neuropathic-Pain-Diagnosis-Simulator
May 2019 - Jan 2023
Neuropathic Pain Diagnosis Simulator
Contributions:53 commits, 48 pushes in 3 years 8 months
simulatordiagnosiscomputational-neuroscienceneurons
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.