Cenk Çorapci
Data Engineer
Haarlem
Summary
Dedicated and experienced Data Engineer with a strong background in researching, developing, and deploying machine learning projects and infrastructure at scale. Worked primarily on e-commerce and classified ads domains, with additional experience in finance. Experienced in search engines, recommendation engines, natural language processing, time series data, deep learning, backend engineering and distributed systems with a balanced blend of research and practical application.
Overview
9
9
years of professional experience
4039
4039
years of post-secondary education
2
2
Languages
Work History
Data Engineer
Adyen
10.2024 - Current
- Lead the project of migrating legacy etl pipelines to a new architecture focused on improving pipeline reliability, reducing latency, and refactoring legacy components to support a scalable and maintainable architecture. In this process, I reduced the alerts and data validation errors by a large margin while handling terabytes of financial payment data across global markets.
Senior Data Engineer
Adevinta (eBay Classifieds Group)
03.2022 - 10.2024
- Worked on iCas, the advertisement bidding engine that serves marketplaces like Marktplaats and Kleinenzeigen. Lead a team to deliver a complete new version of click through rate prediction pipeline which brought %8 increase in revenue.
- Lead the efforts of migrating the internal a/b testing tool called Labs from on-prem to AWS, decreasing the resource usage around %30 while still handling above 10k req/sec loads under 10ms response time.
- Developed and scaled ML pipelines and backend infrastructure for platforms like Marktplaats and eBay Kleinanzeigen serving for ad recommendation and internal analytics dashboards.
- Designed and implemented a system with generative AI and LLMs to improve search engine indexing by creating generated text content.
- Helped migrate legacy systems from on-prem servers of eBay (Nomad stack) to GCP and then AWS reducing technical debt and preparing platforms for long-term maintainability.
- Mentored junior engineers and championed best practices in coding, observability, and documentation.
Machine Learning Engineer
Cimri.com
04.2020 - 02.2022
- Founded a new team of 3 engineers and built Cimri.com's first ML platform from the ground up.
- Built end-to-end NLP pipelines for product matching in an e-commerce setting, from data ingestion to model training and deployment. Utilizing data lake architecture, batch jobs with apache spark and stream processing pipelines with akka-streams/Kafka.
- Published a conference paper which was the state of the art at that time for e-commerce product matching and is this method is still in production at Cimri.com
- Applied PyTorch and Spark for large-scale model training and served predictions through APIs for real-time applications.
- Designed and implemented an image search system based on contrastive represantation learning methods, handling over 20m images for internal data cleaning purposes which reduced the time data clerks needed to clean the data significantly.
Machine Learning Engineer
OBSS
07.2019 - 04.2020
- Designed and implemented machine learning models for autonomous navigation and control of unmanned surface vehicles.
Software & ML Engineer
Cimri.com
10.2016 - 06.2019
- Took part in migration of the platform from a monolithic architecture written in Java to a microservices architecture written in Scala. In this project, I started as a Jr in a team of 5 and ended in founding the first machine learning team and setting the foundations for the companies the data platform. I went through the process of Cimri.com's small tech team becoming a 50 people department and experienced all the challenges of a start-up becoming a scale-up.
- Built and optimized data pipelines for the data analytics platform, enabling real-time processing, aggregation, and updates of e-commerce data from over 400 sites hourly.
Education
Master of Science - Computer Engineering
Yeditepe University
Istanbul Sep 2017 - 07.2021
Bachelor of Science - Computer Engineering
Kocaeli University
Kocaeli Sep 2010 - 01.2017
Tech Stack
Languages: Python, Scala, Go, Java
Streams: Kafka, AWS Kinesis, GCP Pub/Sub
Data Tools: Apache Spark, GCP DataFlow, AWS Athena, AWS EMR
Frameworks: Apache Beam, Flask, PySpark, Akka, Akka-HTTP, Akka-Streams
DevOps: GitLab, Jenkins, GitHub Actions, Terraform, Apache Airflow
Data: Delta Lake, Cassandra, PostgreSQL, Redis, Milvus, GCP BigTable, ElasticSearch, Amazon Athena, GCP BigQuery, ClickHouse
Observability: Redash, Looker, ELK Stack, Grafana
Cloud Platforms: AWS, GCP
Machine Learning: AWS SageMaker, MlFlow, PyTorch
Publications
- Corapci, C. & Yildirim, F. E-Commerce Product Matching with Deep Learning. 2020 International Conference on Computational Linguistics and Natural Language Processing (CLNLP 2020). [Accepted as oral presentation]
Timeline
Data Engineer
Adyen
10.2024 - Current
Senior Data Engineer
Adevinta (eBay Classifieds Group)
03.2022 - 10.2024
Machine Learning Engineer
Cimri.com
04.2020 - 02.2022
Machine Learning Engineer
OBSS
07.2019 - 04.2020
Software & ML Engineer
Cimri.com
10.2016 - 06.2019
Master of Science - Computer Engineering
Yeditepe University
Sep 2017 - 07.2021
Bachelor of Science - Computer Engineering
Kocaeli University
Sep 2010 - 01.2017
Similar Profiles
Dipankar ChakrabortyDipankar Chakraborty
Technical Program Manager at AdyenTechnical Program Manager at Adyen
Kalyan VorugantiKalyan Voruganti
Linux System Engineer at AdyenLinux System Engineer at Adyen
Benjamin StaffordBenjamin Stafford
EMEA Treasury Partnerships Manager at AdyenEMEA Treasury Partnerships Manager at Adyen
Dara PericDara Peric
Senior Analyst, Sales Compensation at Bentley SystemsSenior Analyst, Sales Compensation at Bentley Systems
Baris BaskilicBaris Baskilic
Admin Procurement Officer at TCS (Tata Consultancy Services Netherlands B.V.)Admin Procurement Officer at TCS (Tata Consultancy Services Netherlands B.V.)