I'm a Data Scientist in the Advisory Group at McDaniel, Canada's largest reserves evaluator. My professional scope covers two primary domains:– Execution of complex Machine Learning projects in the oil and gas upstream sector across the Western Canadian Sedimentary Basin. These projects are dedicated to identifying optimal development strategies, with a CAPEX of up to $250 million, through the integration of technical, statistical, and economic analyses.– Development of an advanced analytics platform for monitoring upstream data - including geology, drilling, completions, and production - across Canada and the US, encompassing over 1 million wells and more than 10 million barrels per day.

– Development, implementation, and improvement of Machine Learning software products in heavy industries: oil and gas, metallurgy, coal mining.– Complete data pipeline: from Data Mining & Preparation to ML & AI Ops– Leading a team of 5 engineers: Data Scientists, Business Analysts and Subject Matter Experts– Daily interaction with Client’s Product Owners and various stakeholders: managers and engineers.– Project lead for the internal assessment of Machine Learning and Data Science platforms.– Solid experience with Python: pandas, numpy, scipy, matplotlib, seaborn, sklearn, tensorflow and many others.

– Leading the whole Engineering cycle to deliver ERD wells for the Client in proper time/budget in accordance with a safe and effective way. – Preparation of drilling program for ultra-ERD wells with up to 9000 m MD and 1600 m TVD– Calculation of technical and commercial feasibility– Tracking and evaluation of KPIs– Conducting of offset well analyses – Time estimates. Time versus Depth for various geological and technological scenarios– Communicating with Client, Schlumberger Business Lines and Sub-contractors.On nights and weekends:– ML product development for the prevention of stuck pipe events. Tools used: Python (Pandas, Numpy, Scipy, sklearn, TKinter, Seaborn), Javascript, SQL, REST API, Dataiku, PowerBI– Author of SPE-206516-MS (Prediction of Stuck pipe events on ERD-wells using machine learning algorithms) which was published at SPE’s JPT main page: https://jpt.spe.org/machine-learning-aids-early-detection-of-stuck-pipe-in-extended-reach-wells