Abinash Panda
CTO & Co Founder at Prodios
Delhi, India
Summary
🤩
Rockstar🎓
Top SchoolAbinash Panda is a CTO and co-founder with 11 years of experience building data-driven products and startups from Delhi, India. He combines deep applied machine learning and backend engineering expertise—evidenced by contributions to pgmpy, a prominent Python library for Bayesian and causal inference—with hands-on leadership at Prodios and prior startups like BOCS. His background spans end-to-end analytics platforms, scalable energy disaggregation systems, and production-grade tooling for high-throughput data pipelines. Abinash has a track record of turning research-grade inference and structured-output techniques into robust, monitored services used in real products. Comfortable in both founding and senior engineering roles, he blends technical stewardship with product-minded execution. He holds a B.Tech. in Electronics Engineering from IIT (BHU) Varanasi.
11 years of coding experience
5 years of employment as a software developer
Bachelor of Technology (B.Tech.) Electronics Engineering, Bachelor of Technology (B.Tech.) Electronics Engineering at IIT (BHU) Varanasi
English, Odia, Hindi
Stackoverflow
373reputation
36kreached
3answers
13questions
Github Skills (13)
bayesian-network10
inference10
python10
causal-inference10
testing9
struct8
structures8
pandas7
docker6
azure6
azure-web-app-service6
azure-webapp6
rdlc6
Programming languages (4)
Github contributions (5)
pgmpy/pgmpy
Mar 2015 - Aug 2015
Python Library for learning (Structure and Parameter), inference (Probabilistic and Causal), and simulations in Bayesian Networks.
Role in this project:
Back-end Developer / Data Scientist
Back-end Developer / Data ScientistContributions:24 commits, 43 PRs, 34 pushes in 5 months
Contributions summary:Abinash primarily contributed to the development and maintenance of the `pgmpy` library, focusing on core functionalities related to Bayesian Networks and causal inference. Their work involved fixing bugs in existing methods, such as `to_junction_tree()` in `MarkovModel`, and adding corresponding test cases. The user also improved code efficiency and accuracy by modifying the `get_factors` method in the `ClusterGraph` class and fixing bugs related to the `_is_converged()` method. Furthermore, the user refactored the `BayesianModel` class by introducing the use of an estimator.
causal-modelspythondagbayesian-inferencecausal
dopplr-labs/tail-kit
Aug 2020 - Jul 2022
React UI kit built using tailwindcss
Contributions:45 reviews, 322 commits, 59 PRs in 1 year 10 months
react-ui-kitreacttailwindcsstailwindreactjs
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.