Hasan Ali

Full Stack Data Scientist working on a problem solved by only 4 other companies in the world

Noida, India

Summary

A self-learned Full-Stack Data Scientist with 2+ years of experience building complex data processing applications, anomaly detection & machine learning models along with tackling challenging architectural and scalability problems in IoT. Currently helping Indian Oil with terabyte-scale data pipelines and detecting defects in oil pipelines through autonomous AI

Languages:

English, Hindi

Favorite Python Packages:

pandas, numpy, TensorFlow, opencv, scikit-learn,

Experience

Full Stack Data Scientist Alethe Labs Pvt. Ltd.

Dec 2018 - Present

Alethe was working for Indian Oil to detect their oil pipeline defects from sensor data in PIG(a device that runs inside the oil pipelines constantly collecting data) . This problem was solved by only 4 other companies in the world. We were a team of 7 people (4 data people)

• Built Batch processing pipelines of sensor data from scratch using Apache Spark and Python.
• Did deep research analysis for signal reconstruction and regeneration using different DSP techniques.
• Used OpenCV for augmenting and filtering the images created from signal and figured a method to detect anomalies in the data using bunch of image filtration techniques.
• Built various API's in flask for different business use-cases for multiple development teams .
• Built fully connected CNN for feature/defect predictions in the Indian OIl pipeline.

Data Analyst at TagTaste

Oct 2017 - Dec 2018

Tag Taste is a social media platform for food people like Chef, Hotel Managers, Food Businesses, tasters etc.

• Collaborated with different business stakeholders to report growth on various KPI's of the product.
• Built the entire dashboard to track the KPI and report month on month growth.
• Segmented the users into 8 clusters/buckets by performing NLP on the type of content they posted and their profile data.
• Built content based recommendation

Skills

Artificial Intelligence (AI), Data Science, Docker, Flask, Git, Google Cloud Platform (GCP), Keras, Kubernetes, Machine Learning, MySQL, NumPy, Pandas, Spark, TensorFlow, wxPython