Assistant Manager/Data Science Engineer

Under the supervision of the offshore Data Science Engineering Manager utilizing agile methods of project management:
Acquisition products (Bingxin):
Create and maintain ETL pipelines using PySpark and other tools, handle large, complex data pipelines with AWS technology stack
Models, DNA ETL code pipeline development including identifying new opportunities
Understanding business strategies behind the current production jobs
Implement DevOps practices, including CI/CD and version control with Git
Code improvement/optimization recommendations considering speed, resources utilization and efficiency
Collaborate on coding, manage feature development branches and raise/review pull requests using Bitbucket
Deploy models using cloud-based strategies and make recommendations on improving model efficiency, performance deployment mechanisms
Utilize AWS services such as SageMaker, EC2, S3, and Lambda for data engineering and model deployment
Execution of our end-to-end campaign targeting engine involves updating the ETL/DNA processes, machine learning models, direct mail assignment module, and measurement module, utilizing CI/CD tools and the AWS technology stack
Lead the execution of campaigns and ensure comprehensive support throughout the campaign lifecycle, from design to measurement and optimization

Personalization products (Hazim):
Develop and optimize ETL pipelines using AWS Glue and PySpark for efficient data processing.
Optimize Spark parameters to reduce run times and improve resource utilization.
Build and refine machine learning models using AWS SageMaker for personalization and recommendation systems
Preprocess and clean data to ensure high-quality input for models
Use SQL for querying and managing large datasets
Deploy models to production using AWS SageMaker, ensuring scalability and performance.
Containerize applications using Docker for efficient deployment across environments
Set up CI/CD pipelines with Jenkins and AWS services to automate build, testing, and deployment processes
Utilize AWS services including Glue, SageMaker, EC2, S3, and Lambda for data engineering and model deployment
Optimize code and infrastructure for improved speed and efficiency
Work with Bitbucket or any code version control and collaborative development
Support execution of assignments such as collaborative filtering, trip propensity modeling, and engage in test design, measurement, and execution
Lead the execution of campaigns and ensure comprehensive support throughout the campaign lifecycle, from design to measurement and optimization
Lead the full execution of campaigns, including updating data pipelines, refining machine learning models, managing assignment modules, and measuring outcomes, while leveraging CI/CD tools and AWS infrastructure
Collaborate on test design and measurement, focusing on performance analysis, campaign execution, and continuous improvement

Voice of Member:
Build, maintain, and optimize automated ETL pipelines to process and transform large datasets from diverse sources efficiently
Develop and deploy machine learning models, with a focus on NLP, and ensure seamless integration of these models into data pipelines
Implement and manage data ingestion from external APIs, ensuring smooth data flow into existing workflows for analysis and processing
Oversee the organization, querying, and maintenance of large-scale SQL and NoSQL databases, with a focus on text-based data management
Utilize cloud platforms (AWS, Google Cloud, or Azure) for scalable data processing, storage, and workflow automation

Qualifications we seek in you
Minimum Qualifications / Skills
BSc in Computer Science, engineering (or related area), Statistics, Mathematics or equivalent experience

Preferred Qualifications/ Skills
Experience in algorithms, data structures, and object-oriented programming
Experience in developing Machine learning models for retail use cases
Experience in crafting ad hoc data mining analysis for retail use cases
Proven experience in the implementation of machine learning algorithms and applications for production-level systems
Strong programming skills in Python, PySpark, SQL, or Java, with a focus on scalable solutions
Experience with cluster-computing frameworks (e.g., Spark, Hadoop) and optimizing them for performance and resource efficiency
Expertise in configuring and managing large, complex data pipelines using AWS services (e.g., Glue, SageMaker, Lambda), with experience in GCP/Azure as a plus
Familiarity with DevOps tools and processes, including CI/CD pipelines, version control (Git), and automation tools like Jenkins
Experience with AWS Glue for ETL processes and Spark parameter optimization for performance improvement
Experience using development and collaboration tools like Jira and Confluence
Ability to extract actionable insights from complex datasets using data mining, statistics, and database techniques to improve member acquisition/engagement KPIs
Strong communication and collaboration skills, working effectively across teams and stakeholder