Ankur Ankan
Postdoctoral Researcher at pgmpy
Amsterdam, North Holland, Netherlands
Summary
🤩
Rockstar🎓
Top SchoolAnkur Goel is a Director of Engineering based in Mumbai with 13 years of experience building high-velocity Developer SaaS and fintech platforms. He coaches and scales engineering teams while driving pragmatic system and backend design focused on performance, simplicity, and collaboration. His career at BrowserStack and Drip Capital spans hands-on roles from software engineer to senior leadership, giving him deep operational and product-facing experience. Ankur contributes to open-source probabilistic graphical models—adding EM-based parameter estimation to pgmpy—which reflects a strong interest in applied ML and rigorous probabilistic methods beyond typical infra work. He blends a practical engineering mindset with formal learning in databases and machine learning from Stanford and BerkeleyX, enabling him to translate complex algorithms into production-ready services.
13 years of coding experience
2 years of employment as a software developer
Doctor of Philosophy - PhD, Causal Inference, Doctor of Philosophy - PhD, Causal Inference at Radboud UniversityMaster's degree, Artificial Intelligence, Master's degree, Artificial Intelligence at Radboud University NijmegenB.Tech, Electronics and Communications Engineering, B.Tech, Electronics and Communications Engineering at Indian Institute of Technology (Banaras Hindu University), Varanasi
Hindi, English
Github Skills (5)
probabilistic-graphical-models10
jupyter-notebook10
python10
documentation10
machine-learning8
Programming languages (7)
Github contributions (5)
pgmpy/pgmpy_tutorials
Nov 2014 - May 2022
Tutorials on Causal Inference and pgmpy
Role in this project:
Technical Writer
Technical WriterContributions:68 commits, 19 PRs, 57 pushes in 7 years 6 months
Contributions summary:Ankur's commits primarily focus on creating and updating documentation for a tutorial on Probabilistic Graphical Models (PGM) using the `pgmpy` library. The initial commit introduces the tutorial with a notebook on PGM, and subsequent commits add content, structure, and formatting to both a Jupyter Notebook and a slideshow presentation of the tutorial. This suggests a focus on explaining complex concepts, and creating easy to understand examples.
causal-inferencecausal-discoverycausal-graphscausal-identificationcausal-prediction
pgmpy/pgmpy
Sep 2013 - Jan 2023
Python Toolkit for Causal and Probabilistic Reasoning
Role in this project:Back-end Developer
Back-end DeveloperContributions:15 releases, 527 reviews, 1643 commits in 9 years 5 months
Contributions summary:Ankur implemented and modified the `BayesianEstimator.py` module to add functionality for estimating parameters using the Expectation-Maximization algorithm. They incorporated the weighted version of the Maximum Likelihood Estimator in EM and improved tests for this functionality, showcasing work on parameter estimation for Bayesian Networks. The user also added code for a custom function to measure the likelihood.
probabilistic-reasoningpythonbayesian-networkscausal-inferencecausal-discovery
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.