Highlights:

Skills:Python, SQL, Google Cloud Platform, GCP, Spark, Hadoop, Databricks, Backend, Full Stack, Airflow, Dataflow, BigQuery, Machine Learning, AI, LLM, NLP, Pandas, Numpy, Scikit-learn, Matplotlib, seaborn, Tensorflow

Certification:Google Cloud Platform (GCP) Professional Machine Learning Engineer https://www.credly.com/earner/earned/badge/02ff1e86-1ad0-4e80-b3c6-ae724f2d6fd0 DeepLearning.AI Machine Learning Specialization https://www.coursera.org/account/accomplishments/specialization/2VP2Y5FDCSTZ

Data Engineer 01/2024 - current
BT Group, London, Greater London United Kingdom
Industry: Telecommunications
-Development of GCP BigQuery stored procedures on Gitlab in a CI/CD scheduled pipeline
-Implementation and monitoring of Data Quality checks on key business metrics using Airflow to enhance data integrity -Streamlining E2E delivery of code updates and new source builds into existing stacks, reducing downtime by covering multiple roles’ responsibilities -Development and maintenance of automated BigQuery Audit Log tables to ensure fails are documented, notifications sent, and actions taken -Ingestion of Kaplan Maier survival analysis scoring data to calculate expected tenure and revenue for customers, aiding in business decisions -Build and implementation of Hybrid Recommender System powered customer shop platform and interactions data into BigQuery tables for BI reporting on Qliksense -Refactoring existing architecture to combine major sources of data, documenting changes and impacts for technical and non-technical stakeholders -Repointing of data during migration from on-premise to Cloud storage for improved scalability and flexibility--
Data Engineer 08/2023 - 01/2024
Hercules Project, London, Greater London United Kingdom
Industry: IT
-Ingested Coresignal LinkedIn API data using Databricks through Bronze, Silver and Gold Pipeline for use in Market Penetration Analytics, delivering business insights to CTO and CEO
-Implemented PySpark and SparkSQL parallelised transformations (Silver layer) from entry point (Bronze layer) to Tableau (Gold layer), in line with best practices on efficient data processing -Deployed bulk API to optimise processing of 15 million+ job listings, improving delivery time of outputs for visualisation from 2 weeks to daily -Processing of job listings and extraction of keywords in Bronze and Silver layers using BERT, enabling strategic decision making and data-driven competitive advantage--
Data Engineer 03/2022 - 08/2023
HSBC, London, United Kingdom
Industry: Financial Services
-Audit Remediation and Regulatory Reporting projects, successfully aggregating and automating data lineage and assurance reporting for Finance Data
-Architected automated ETL process using Python with OOP best practice to extract data out of sources including Collibra (API) and Excel (Openpyxl), cutting reporting time down from one month to two days -Cleaned and processed data using Pandas for ingestion into SQL Server, with outputs feeding into Qliksense dashboard, delivering Regulatory and Audit reporting achieving near-perfect data quality -Created Gold Standard for Data Lineage architecture, standardising into a high-quality format for use across HSBC Finance teams -Automated Assurance reports for Regulatory Audit using Python (Openpyxl), changing process from manual and weekly to hourly, significantly improving data accuracy--
Data Engineer 11/2021 - current
Kubrick Group, London, Greater London United Kingdom
Industry: IT
-Consultancy oriented work at established clients and internal projects -Training and experience in Data Modelling, Machine Learning, SQL, Python, Databricks, Spark, Hadoop, Beam, Git and producing end to end pipelines using on-premise and Cloud technology
--

University of York 09/2017 - 08/2021
York, North Yorkshire, United Kingdom
Degree: Bachelor's Degree
Major:Economics
Minor:Econometrics
Investment and Finance Society, York Community Consulting, Captain of University Basketball team

Login to view resume: Fuad Gafarzada - engineer