From 46c5af0f4c63ca4d9db9c980725317e47c50b656 Mon Sep 17 00:00:00 2001 From: GitHub Actions Date: Thu, 14 Dec 2023 09:50:20 +0000 Subject: [PATCH] Update GitHub Pages with new index.html --- index.html | 206 ++++++++++++++++++----------------------------------- 1 file changed, 71 insertions(+), 135 deletions(-) diff --git a/index.html b/index.html index b5cb32f..442b40c 100644 --- a/index.html +++ b/index.html @@ -186,7 +186,7 @@

- Python/R Software Engineer | Data Scientist | Statistician | AI/Machine Learning Specialist + Python Software Engineer | Statistician | AI/Machine Learning Specialist

1040, Brussels, Belgium

@@ -274,7 +274,7 @@

Technical competencies

Containerization: - DockerHub, Docker + DockerHub, Docker, Docker compose @@ -319,7 +319,7 @@

Personal details

Rohail Taimour

Summary

-

As a seasoned Python/R Software Engineer and Data Scientist with a Master's degree in Statistics, I specialize in creating robust data products with a focus on machine learning. My dynamic skill set bridges the gap between data science, machine learning engineering, and data engineering, allowing me to thrive in fast-paced, ambiguous environments. I am passionate about enhancing project efficiency and impact through best practices and agile methodologies.

+

Seasoned Python Software Engineer with a Master's degree in Statistics. I am proficient in building applications following best software practices such as CI/CD, containerization and operating in an AWS or Azure cloud environment.

Job History

-

Freelance projects (Oct 2022-present)

+

Relevant Experience

- Multi-Layered Python Solution to Launch and Manage Pipelines for Customer-Uploaded Data, Enabling Automated Report Downloads + End-to-End Orchestration of AWS SageMaker for Production-Grade Machine Learning Pipeline Development

@@ -352,12 +352,12 @@

-

Python Software Engineer and Data Pipeline Architect, Illumina, Mechelen, Belgium

+

AWS Sagemaker Bootcamp with Santiago Valdarrama (70k followers on Linkedin)

-

April 2023 - October 2023

+

Nov 2023-Dec 2023

@@ -365,17 +365,19 @@

    -
  • Designed a Python service that automates the monitoring and processing of customer-uploaded sequencing data, initiating further analysis or report generation based on predefined criteria.
    • +
  • Deployment of complex machine learning pipelines in AWS SageMaker, including data processing, model training, hyperparameter tuning, and model registry management.
    • -
  • Implemented a dual-layered approach: the first layer handles the initiation and tracking of analysis pipelines, while the second layer is registered as a Docker image in the analytics backend to perform post-processing on the output files and create comprehensive summary reports for the customer.
    • +
  • Utilized TensorFlow Estimator for model training within SageMaker, leveraging container images and SageMaker Experiments for enhanced tracking and logging of training processes.
    • -
  • Scheduled the Python service to operate every 30 minutes for new data and updates, ensuring seamless progression from data upload to final report delivery to customer environment.
    • +
  • Incorporated robust model evaluation using SageMaker's Processing and Condition Steps, ensuring models are registered in the SageMaker Model Registry only upon meeting predefined accuracy benchmarks.
    • -
  • Implemented comprehensive systems integration, utilizing a combination of CLI tools and API calls for effective coordination and automation across various software components.
    • +
  • Deployed models to SageMaker Endpoints from the Model Registry, integrating inference pipelines for efficient handling of pre- and post-processing tasks.
    • -
  • Applied Object-Oriented Programming (OOP) principles to organize API, database interactions and endpoint processing to reduce code duplication and utilize self-documenting object names.
    • +
  • Implemented an automated deployment system using Amazon EventBridge and AWS Lambda, enabling dynamic model deployment upon meeting set approval criteria.
    • -
  • Implemented unit testing using pytest and implemented fail-safe mechanisms for robust error handling.
    • +
  • Established Amazon SageMaker Model Monitor schedules to ensure continual assessment and maintenance of model performance via data and model quality checks.
    • + +
  • Explored and planned transition of machine learning pipeline from Keras with TensorFlow backend to PyTorch, utilizing the new Keras 3 API.

@@ -383,7 +385,7 @@

- Automated SQL Script Generation to facilitate PostgreSQL Data Migration in multiple environments + Multi-Layered Python Solution to Launch and Manage Pipelines for Customer-Uploaded Data, Enabling Automated Report Downloads

@@ -391,12 +393,12 @@

-

Python Software Engineer, Illumina, Mechelen, Belgium

+

Python Software Engineer and Data Pipeline Architect, Illumina, Mechelen, Belgium

-

July-Aug 2023

+

April 2023 - October 2023

@@ -404,15 +406,17 @@

    -
  • Designed and implemented a data ingestion framework to parse and validate input files for generating and validating SQL update statements.
    • +
  • Designed a Python service that automates the monitoring and processing of customer-uploaded sequencing data, initiating further analysis or report generation based on predefined criteria.
    • -
  • Conducted comprehensive testing of generated SQL scripts using a mock of production database tables to test that SQL scripts run as expected.
    • +
  • Implemented a dual-layered approach: the first layer handles the initiation and tracking of analysis pipelines, while the second layer is registered as a Docker image in the analytics backend to perform post-processing on the output files and create comprehensive summary reports for the customer.
    • -
  • Utilized SQLAlchemy for database schema management, creating and populating mock tables in a test environment to ensure the integrity and functionality of SQL scripts.
    • +
  • Scheduled the Python service to operate every 30 minutes for new data and updates, ensuring seamless progression from data upload to final report delivery to customer environment.
    • -
  • Implemented the solution as a Python package encapsulating the entire data migration logic within a Docker entrypoint for portability and ease of deployment.
    • +
  • Implemented comprehensive systems integration, utilizing a combination of CLI tools and API calls for effective coordination and automation across various software components.
    • -
  • Leveraged Jinja2 templating to generate dynamic, parameterized SQL scripts, enabling the script to adapt seamlessly across different deployment environments, such as Development, Integration, and Production.
    • +
  • Applied Object-Oriented Programming (OOP) principles to organize API, database interactions and endpoint processing to reduce code duplication and utilize self-documenting object names.
    • + +
  • Implemented unit testing using pytest and implemented fail-safe mechanisms for robust error handling.

@@ -420,7 +424,7 @@

- Design and implement information retrieval methods using Natural language processing (NLP) + Automated SQL Script Generation to facilitate PostgreSQL Data Migration in multiple environments

@@ -428,12 +432,12 @@

-

Machine Learning Engineer, IT Supply Quality, GSK Belgium

+

Python Software Engineer, Illumina, Mechelen, Belgium

-

Oct 2022‑Feb 2023

+

July-Aug 2023

@@ -441,23 +445,23 @@

    -
  • Improved performance of information retrieval by 20% on unseen test data using a custom named entity recognition (NER) from Spacy.
    • +
  • Designed and implemented a data ingestion framework to parse and validate input files for generating and validating SQL update statements.
    • -
  • Performed POC’s on Azure DataBricks environment to improve model performance using rule-based techniques as well as NER and annotated data to train custom NER.
    • +
  • Conducted comprehensive testing of generated SQL scripts using a mock of production database tables to test that SQL scripts run as expected.
    • -
  • Added text preprocessing features to the NLP pipeline such as Spacy tokenization, Part of speech (POS) tagging, better handling of non‑english emails, breaking emails into sentences, etc.
    • +
  • Utilized SQLAlchemy for database schema management, creating and populating mock tables in a test environment to ensure the integrity and functionality of SQL scripts.
    • + +
  • Implemented the solution as a Python package encapsulating the entire data migration logic within a Docker entrypoint for portability and ease of deployment.
    • + +
  • Leveraged Jinja2 templating to generate dynamic, parameterized SQL scripts, enabling the script to adapt seamlessly across different deployment environments, such as Development, Integration, and Production.

- - -

Data science projects at IT AI team, UCB Pharmaceutical (2016‑Oct 2022)

-

- Yield optimization for batch and continuous production processes using Machine Learning in Python + Design and implement information retrieval methods using Natural language processing (NLP)

@@ -465,12 +469,12 @@

-

Lead Data Scientist, Supply and Manufacturing, UCB Switzerland/Belgium

+

Machine Learning Engineer, IT Supply Quality, GSK Belgium

-

Aug 2020‑Oct 2022

+

Oct 2022‑Feb 2023

@@ -478,15 +482,11 @@

    -
  • Production setting proposed by model directly led to an increased throughput of 20%, turning in a recurring 1.5 million euro in annual cost savings
    • - -
  • Analyze time series data collected from equipment sensors and visually summarize golden batch insights
    • - -
  • Created (Bayesian) and tree-based regression models to quantify impact of process changes and predict batch performance
    • +
  • Improved performance of information retrieval by 20% on unseen test data using a custom named entity recognition (NER) from Spacy.
    • -
  • Performed a thorough model validation and hyperparameter tuning exercise before recommending model insights be tested in a live production environment
    • +
  • Performed POC’s on Azure DataBricks environment to improve model performance using rule-based techniques as well as NER and annotated data to train custom NER.
    • -
  • Supported delivery of workshops demystifying the process of conducting AI projects and machine learning to process experts
    • +
  • Added text preprocessing features to the NLP pipeline such as Spacy tokenization, Part of speech (POS) tagging, better handling of non‑english emails, breaking emails into sentences, etc.

@@ -494,44 +494,25 @@

- Promotional Responsiveness-Driven Omni-Channel Marketing and Customer Segmentation in EU5 + Unit Commitment Solver for Power Grid Optimization via FastAPI

-
-
- -
-

AI/ML engineer, Lead Data Scientist, Go to Market/Commercial EU5, US and Japan, UCB

-
- - -
-

June 2019‑June 2021

-
- -
-
-
    -
  • Utilized demographic data for customer segmentation, identifying high-potential growth and revenue segments
    • - -
  • Explored the interaction between customer segments and marketing channel responsiveness, identifying which segments exhibited the highest engagement with specific promotional strategies
    • - -
  • Optimized marketing resource allocation by aligning customers with their most responsive channels
    • +
  • Developed a REST API using FastAPI for optimizing energy distribution among powerplants based on load requirements and fuel costs.
    • -
  • Developed a Python package with Cookiecutter templates that abstract the complexities of the data science workflow, enabling configurable deployments across diverse scenarios such as different countries and disease areas.
    • +
  • Implemented multiple algorithms to solve the unit-commitment problem, considering factors like fuel cost, powerplant efficiency, and environmental constraints.
    • -
  • Enhanced the package to seamlessly wrap over scikit-learn, thereby simplifying key data science tasks from preprocessing to model training and tuning
    • +
  • Utilized Pydantic for data validation and schema definition, ensuring data integrity and streamlined request handling.
    • -
  • Incorporated MLflow into the package for robust artifact management, allowing for the tracking of model versions, data inputs, and predictions
    • +
  • Packaged and containerized the application using Docker, with detailed documentation and a Dockerfile for easy deployment and scalability.
    • -
  • Created customer segmentation models and proposed optimal resource allocation based on customer responsiveness to different marketing channels
    • +
  • Employed pytest, along with Python best practices such as typing and linting.
    • -
  • Investigated adaptations to data science methodology for country/product specificities for maximum reusability. Delivered as many as ten different use cases for different products and countries
    • +
  • Managed project dependencies using Poetry, facilitating efficient workflow and package management.
    • -
  • Performed feature engineering using PySpark and validated ingested data using data visualization methods and discussions with subject-matter experts
    • +
  • Deployed the API service using Uvicorn and integrated a Swagger UI for interactive API documentation and testing
@@ -539,7 +520,7 @@

- Scientific influencer (KOLs) identification, ranking and profiling using network analytics and Neo4j + Yield optimization for batch and continuous production processes using Machine Learning in Python

@@ -547,12 +528,12 @@

-

Data scientist/Product owner, Drug Development, Commercial, Medical affairs, UCB

+

Lead Data Scientist, Supply and Manufacturing, UCB Switzerland/Belgium

-

2018‑2019

+

Aug 2020‑Oct 2022

@@ -560,13 +541,15 @@

    -
  • Developed custom Neo4j databases integrating diverse data sources for KOL influence analysis, enhancing data-driven decision-making.
    • +
  • Production setting proposed by model directly led to an increased throughput of 20%, turning in a recurring 1.5 million euro in annual cost savings
    • -
  • Utilized py2neo within Jupyter Notebooks for interactive data manipulation and network visualizations, employing tools like NetworkX and Cytoscape for insightful analysis.
    • +
  • Analyze time series data collected from equipment sensors and visually summarize golden batch insights
    • -
  • Interacted with the Graph database via Cypher queries in the web UI as well as via the CLI for data extraction, exploration and reporting.
    • +
  • Created (Bayesian) and tree-based regression models to quantify impact of process changes and predict batch performance
    • -
  • Supported improvements in the intake of customer requests to reduce time to deliver reports from days to hours
    • +
  • Performed a thorough model validation and hyperparameter tuning exercise before recommending model insights be tested in a live production environment
    • + +
  • Supported delivery of workshops demystifying the process of conducting AI projects and machine learning to process experts

@@ -574,7 +557,7 @@

- Developed an Automated Forecasting Workflow of Claims Data from US Healthcare System + Marketing Mix Optimization and Customer Segmentation modelling in EU5

@@ -582,12 +565,12 @@

-

Lead Data Scientist, US Finance and claims, UCB

+

AI/ML engineer, Lead Data Scientist, Go to Market/Commercial EU5, US and Japan, UCB

-

2017‑2018

+

June 2019‑June 2021

@@ -595,46 +578,25 @@

    -
  • Engineered specialized R packages focusing on separate concerns: data engineering for preprocessing, a wrapper over Facebook's Prophet for advanced forecasting, and automated reporting for performance analysis.
    • +
  • Utilized demographic data to develop customer segmentation models, identifying key segments for high-potential growth and revenue.
    • -
  • Designed and implemented a comprehensive end-to-end workflow for ingesting healthcare claims data, performing time-series forecasting, and generating insightful reports on forecasting accuracy.
    • +
  • Integrated multi-channel marketing data, gaining a comprehensive understanding of customer interactions to inform the development of an effective market mix model.
    • -
  • Achieved over 90% forecasting accuracy across various use cases by meticulously tuning models and integrating bespoke anomaly detection algorithms for time series data.
    • +
  • Leveraged the market mix model to investigate the relationship between customer segments and marketing channel responsiveness, pinpointing segments with the highest engagement potential.
    • -
  • Conducted extensive hyperparameter tuning and model validation using high-performance computing to optimize forecasting models effectively.
    • +
  • Aligned the insights from the market mix model with promotional strategies, targeting specific customer segments through their most responsive channels.
    • -
  • Automated report generation using R Markdown, providing clear, concise insights into forecasting performance and model accuracy.
    • +
  • Optimized marketing resource allocation based on the model’s insights, tailoring marketing strategies to enhance customer engagement and maximize ROI across diverse channels.
    • -
-

- -
-

+
  • Adapted data science methodologies to address country and product specificities, delivering tailored solutions for up to ten different use cases across various products and countries.
    • - Hands‑on workshop to demystify Artificial intelligence and Machine Learning +
  • Developed a Python package with Cookiecutter templates that abstract the complexities of the data science workflow, enabling configurable deployments across diverse scenarios such as different countries and disease areas.
    • -

    - -
    -
    - -
    -

    Data science instructor, IT departments US, EU, UCB

    -
    - - -
    -

    May‑ June 2017

    -
    - -
    -
    - -
      +
    • Enhanced the package to seamlessly wrap over scikit-learn, thereby simplifying key data science tasks from preprocessing to model training and tuning
      • -
    • Created a R shiny application to create an engaging way for participants to learn about typical AI use cases
      • +
    • Incorporated MLflow into the package for robust artifact management, allowing for the tracking of model versions, data inputs, and predictions
      • -
    • Delivered the workshop to over 100 people in four different venues and received great feedback on level of engagement
      • +
    • Performed feature engineering using PySpark and validated ingested data using data visualization methods and discussions with subject-matter experts
    @@ -705,32 +667,6 @@

    -
    -

    - - Unit Commitment Solver for Power Grid Optimization via FastAPI - -

    - - -
    -