Experience

• 

  Blaise Transit

  • Canada
  • IT Services and IT Consulting
  • 1 - 100 Employee

  • Research Engineer

    • Dec 2023 - Present

  • Data scientist consultant

    • Jan 2023 - Feb 2024

  • Data Scientist and Operation Research Specialist

    • Mar 2021 - Dec 2022

    𝐃𝐚𝐭𝐚 𝐄𝐧𝐠𝐢𝐧𝐞𝐞𝐫𝐢𝐧𝐠 𝐑𝐞𝐬𝐩𝐨𝐧𝐬𝐢𝐛𝐢𝐥𝐢𝐭𝐢𝐞𝐬:- Designed, implemented and maintained multi-dimensional datawarehouse and data marts forcomplex data flows and data sources.- Managed and built ETL processes, extraction integration of data (including streaming data ) from various data sources.- Lead to migrate Datawarehouse from MySQL server to Microsoft SQL server in Azure.- Created custom data models for automated analysis, training machine learning, and BI reporting.- Designed and developed high-quality visual dashboards, reports and KPI with Power BI- 𝐓𝐞𝐜𝐡𝐧𝐨𝐥𝐨𝐠𝐢𝐞𝐬 𝐮𝐬𝐞𝐝: Python - Bash Scripting - Spark - Azure Data Factory - Azure batch - Azure Synapse - Data Lake - Airflow - MySQL - MS SQL - Power BI - Firebase (No-SQL) - Git - Docker 𝐃𝐚𝐭𝐚 𝐒𝐜𝐢𝐞𝐧𝐭𝐢𝐬𝐭 𝐑𝐞𝐬𝐩𝐨𝐧𝐬𝐢𝐛𝐢𝐥𝐢𝐭𝐢𝐞𝐬:- Took a lead on defining data science problems and developing innovative solutions using machinelearning, optimization models, and advanced statistics- Prepared, parsed and integrated large and varied structured and unstructured data such as geospatial, time-series, graph-based data sets to build statistical, machine learning models, optimization model- Developed Python scripts, bash scripts, DevOps pipeline to automate manual processes and tests in Blaise- Developed Machine Learning models to predict passengers trip origin destination (OD)- Designed and developed a sentiment analysis and key extraction model to analyze and classify comments using the NLP transformer models- 𝐓𝐞𝐜𝐡𝐧𝐨𝐥𝐨𝐠𝐢𝐞𝐬 𝐮𝐬𝐞𝐝: Python - Bayesian Optimization - Bash Scripting - Git - Docker - Azure DevOps - PyTorch - Keras - Emukit - GIS packages𝐎𝐭𝐡𝐞𝐫 𝐑𝐞𝐬𝐩𝐨𝐧𝐬𝐢𝐛𝐢𝐥𝐢𝐭𝐢𝐞𝐬:- Designed, created, and solved constrained shortest path (CSP) models to respond on-demand requests- Created, customized, and deployed the road network on OSRM server- 𝐓𝐞𝐜𝐡𝐧𝐨𝐥𝐨𝐠𝐢𝐞𝐬 𝐮𝐬𝐞𝐝: QGIS - OSRM - CSPY - NetworkX

• 

  Xplore Inc.

  • Markham, Ontario, Canada

  • Data Scientist

    • Jan 2023 - Dec 2023
    • Markham, Ontario, Canada

    Data Engineering Experience:· Architected and implemented scalable ETL pipelines for real-time big data from multiple sources using industry-leading technologies such as Airflow and Kafka.· Spearheaded the adoption of Gitlab CI/CD, successfully automating pipeline build, testing processes.· Proficiently managed and maintained a Postgres database on-premise server, ensuring data integrity and optimal performance.· Led the migration of the Postgres database to Timescale DB, enhancing data storage capabilities and retrieval efficiency.· Conducted thorough optimization of the database for timeseries and geospatial data, resulting in a remarkable 100x reduction in query time for timeseries and a 10x improvement for geospatial data.DevOps Experience:· Established and implemented Docker Swarm services, effectively managing multiple server nodes and ensuring seamless orchestration of containerized applications.· Successfully deployed a range of open-source services, including but not limited to Airflow, Kafka, TimescaleDB, Dask, Minio, MLflow, Grafana, Loki, showcasing versatility in technology stack management.· Setup and deployed Loki and Promtail services in production environments, streamlining the collection and pushing of Docker Swarm services logs to Grafana for centralized monitoring.Data Science Experience:· Conceptualized and developed a Python geospatial application tailored for IT, providing real-time insights into the best available cell options for new customers through a fast API.· Implemented and meticulously fine-tuned spatiotemporal models utilizing to forecast both short-term and long-term demands for customers.· Engineered and optimized a scalable timeseries model incorporating past and future covariate features, enabling the precise forecasting of congestion for over 25,000 cells. Pioneered the automation of reports and geospatial analyses in Python, streamlining processes and enhancing efficiency in data-driven decision-making.

• 

  AltaML

  • Calgary, Alberta, Canada

  • Associate Machine Learning Developer

    • Jul 2021 - Oct 2021
    • Calgary, Alberta, Canada

• 

  University of Calgary

  • Canada
  • Higher Education
  • 700 & Above Employee

  • Research Assistant

    • Mar 2020 - Jun 2021

    Intelligence transportation researcher with supervision of Prof. Lina Kattan. My research is using GCN (Graph Convolution Network) and LSTM to find the propagation pattern during collision at network level. This research could be useful in next generation navigation system specially in smart cities with connected and autonomous vehicles.Proposed research is using diffusion process to obtain travel time information not only the adjacent road of main accident road, but also the k-th hopping road to predict congestion effect in a network around accident. The data are deployed in this research is provided with INRIX company. Tech/ML: Python, Jupyter Notebook, Numpy, Pandas, Matplotlib, PyTorch, SciPy

  • Research Assistant

    • Oct 2019 - Mar 2020

    Compound Generalized Extreme Value distribution for modeling the effects of monthly and seasonal variation on the extreme travel delays for vulnerability analysis of road networkI participated as programmer in this research.I analyzed high resolution historical travel time and accident data from the City of Calgary. The statistical analysis performed on the data was overly complex given the size and details of the travel time data (6 years of travel time data for 5104 links in Calgary road network with the resolution of 1 minute).- Extracting data from INRIX server, cleaning, processing data based on the developed model using Pandas- Implementing the Compound Generalized Extreme Value using SciPy.- Do the hypothesis test and fit distribution using Openturns library- Clustering data with k-means, Ck-means, Hierarchical clustering, and DBSCAN

  • Teaching Assistant

    • Sep 2019 - Jan 2020

    Python instructor– Civil Engineering Aspects of Sustainable Community

• 

  Ecomotive

  • Iran

  • Data Analyst

    • Oct 2017 - Dec 2018
    • Iran

    Designed database schema contains over 30 tables using one-to-many, many-to-one, many-to-many relationshipsBuilt queries (MySQL, SQL, and Postgres)Develop and implement data collection systems, data analytics and dashboards within PowerBIDevelop insight solutions that deliver simple, compelling and actionable data visualizations.Work with stakeholders to identify, analyze, and interpret trends or patterns in complex data sets (e.g., financial, healthcare);Organize and correlate data from disparate data systems to create and build data storiesAssist with database design and developmentMake script and automate process

• 

  Amirkabir University of Technology - Tehran Polytechnic

  • Tehran, Iran

  • Teaching Assistant

    • Sep 2016 - Sep 2017
    • Tehran, Iran

    Statistics for Engineering: Matlab Lab instructorOperation Research 2: GAMS instructor