A full-stack data science professional with 7+ years of work experience, who enjoys developing end-to-end data science solutions to provide valuable insights and support data-driven decision-making. Ample experience collaborating with stakeholders to identify and gather project requirements, communicating findings, and contribute to other aspects of project management.
Berlin, Germany
October 2021 - Present
- Leading and coordinating development of different cross-team BI and Data Science projects.
- Develop, implement, and automating deployment of ETL workflows using DBT and Redshift DWH.
- Competitive Intelligence - crawl and analyze the data from competitors to drive insights using NLP.
- Analyzing feature usage data to understand customer behavior, predict conversion, and lead generation.
- Detecting product's commercial usage using machine learning to push for free-to-paid conversion.
- Generated country embeddings using relational data to identify geographic/demographic resemblance.
- Clustering 200Mn+ users to tune marketing campaigns and generate sales opportunities.
- Conducting hiring interviews, providing mentorship and onboarding junior colleagues.
July 2020 - October 2021
- Established a central framework and delivered end-to-end pipelines for 7+ ML projects into production.
- Recommender systems - Session-based (RNN), Collaborative Filtering (ALS) and Content-based.
- Product matching for 20Mn+ hotels using Fuzzy Pattern, NLP algorithms, and rule-based models.
- Time-series forecasting of hotel prices for next 90 days across 500+ cities using LSTM, ARIMA models.
- Customer journey mapping to understand user preferences before finalizing the purchase on website.
- Classify 13,000+ incoming mails every week using Text vectorization (NLP) and SGD classifier.
- Identifying 78% of the booking and voucher frauds using a random forest anomaly detection model.
- Created a RASA chatbot to help customers find answers to booking related questions and requests.
February 2018 - July 2020
- Deep Q-learning to train an autonomous car to navigate in an Industry 4.0 environment.
- Statistical and deep learning models for low latency (~3.8s) anomaly detection on acquired sensor data.
- Developed, tested, deployed, and managed continuous delivery and automation pipeline for this solution.
- Interactive visual explanations for results to understand, root-cause, and fix anomalous events.
- Deployed neural network models on resource-constrained devices using connection pruning strategies.
- Compressed computer vision deep learning models to 40% of original size with only a 6% accuracy drop.
- Presented technical papers to summarize the work and findings at the university and partner company.
February 2015 - October 2017
- Developed emulation solutions - supporting 7+ clients, with a focus on system-level design / verification.
- Managed a team of 4 and involved in hiring resources, onboarding, and delivering training workshops.
Signal, Image, and Speech Processing, with a 1.7 GPA
Thesis: Using Deep Learning for Anomaly Detection on Autonomous Systems
Research Papers:
Majored in Microelectronics and graduated with 82%
Thesis: Dual Axis Solar Tracking System
End-to-end pipeline for mail classification and text recognition from doctor bills for a veterinary institution.
Freiburg Hackathon 2020 : Developed Medical Assistance Chatbot using RASA framework.
Paraphrase detection for identical representation of text using syntactic and semantic analysis.
Udacity Nanodegree: Simulating self-driving Cars using deep learning with RADAR and LiDAR data.
A full-stack data science professional with 7+ years of work experience, who enjoys developing end-to-end data science solutions to provide valuable insights and support data-driven decision-making. Ample experience collaborating with stakeholders to identify and gather project requirements, communicating findings, and contribute to other aspects of project management.
Berlin, Germany
October 2021 - Present
- Leading and coordinating development of different cross-team BI and Data Science projects.
- Develop, implement, and automating deployment of ETL workflows using DBT and Redshift DWH.
- Competitive Intelligence - crawl and analyze the data from competitors to drive insights using NLP.
- Analyzing feature usage data to understand customer behavior, predict conversion, and lead generation.
- Detecting product's commercial usage using machine learning to push for free-to-paid conversion.
- Generated country embeddings using relational data to identify geographic/demographic resemblance.
- Clustering 200Mn+ users to tune marketing campaigns and generate sales opportunities.
- Conducting hiring interviews, providing mentorship and onboarding junior colleagues.
July 2020 - October 2021
- Established a central framework and delivered end-to-end pipelines for 7+ ML projects into production.
- Recommender systems - Session-based (RNN), Collaborative Filtering (ALS) and Content-based.
- Product matching for 20Mn+ hotels using Fuzzy Pattern, NLP algorithms, and rule-based models.
- Time-series forecasting of hotel prices for next 90 days across 500+ cities using LSTM, ARIMA models.
- Customer journey mapping to understand user preferences before finalizing the purchase on website.
- Classify 13,000+ incoming mails every week using Text vectorization (NLP) and SGD classifier.
- Identifying 78% of the booking and voucher frauds using a random forest anomaly detection model.
- Created a RASA chatbot to help customers find answers to booking related questions and requests.
February 2018 - July 2020
- Deep Q-learning to train an autonomous car to navigate in an Industry 4.0 environment.
- Statistical and deep learning models for low latency (~3.8s) anomaly detection on acquired sensor data.
- Developed, tested, deployed, and managed continuous delivery and automation pipeline for this solution.
- Interactive visual explanations for results to understand, root-cause, and fix anomalous events.
- Deployed neural network models on resource-constrained devices using connection pruning strategies.
- Compressed computer vision deep learning models to 40% of original size with only a 6% accuracy drop.
- Presented technical papers to summarize the work and findings at the university and partner company.
February 2015 - October 2017
- Developed emulation solutions - supporting 7+ clients, with a focus on system-level design / verification.
- Managed a team of 4 and involved in hiring resources, onboarding, and delivering training workshops.
Signal, Image, and Speech Processing, with a 1.7 GPA
Thesis: Using Deep Learning for Anomaly Detection on Autonomous Systems
Research Papers:
Majored in Microelectronics and graduated with 82%
Thesis: Dual Axis Solar Tracking System
End-to-end pipeline for mail classification and text recognition from doctor bills for a veterinary institution.
Freiburg Hackathon 2020 : Developed Medical Assistance Chatbot using RASA framework.
Paraphrase detection for identical representation of text using syntactic and semantic analysis.
Udacity Nanodegree: Simulating self-driving Cars using deep learning with RADAR and LiDAR data.