Lead ML Engineer
Coda Platform Ltd
(Internet and Information Technology, 10-50 employees)
Keywords
Skills
Get in touch for a FREE consultation call before working together.
I aim to incorporate AI into your business, and make it useful in the real world. This means getting the most out of the data that you have, within the context of the systems you have already built. I have not only worked on terabyte-scale data and productionised ML models, but also created user-friendly visualisations so that all insights can be actioned much more confidently.
I aim to incorporate AI into your business, and make it useful in the real world. This means getting the most out of the data that you have, within the context of the systems you have already built. I have not only worked on terabyte-scale data and productionised ML models, but also created user-friendly visualisations so that all insights can be actioned much more confidently.
Project history
11/2019
-
02/2021
Initiated the startup's data science function. I grew out the team and designed and implemented the architecture behind the ML systems. This streamlined development work and led to ongoing LTV, Retention, ARPU and IMPU improvements.
Productionised ML models in both the cloud and edge (mobile) devices, embedded within our SDK. Models include predicting LTVs, categorising new games based on their screenshots and an optimised monetisation setup for games.
Integrated segmentation within AB Testing, so that each user segment can be served the optimal player experience.
Evangelised good research practices, enabled data-driven decisions and fostered a fun and collaborative culture.
Productionised ML models in both the cloud and edge (mobile) devices, embedded within our SDK. Models include predicting LTVs, categorising new games based on their screenshots and an optimised monetisation setup for games.
Integrated segmentation within AB Testing, so that each user segment can be served the optimal player experience.
Evangelised good research practices, enabled data-driven decisions and fostered a fun and collaborative culture.
11/2015
-
10/2019
Data Science Team Lead
IG Index Ltd
(Banks and financial services, 1000-5000 employees)
Grew the company’s Data Science department, and managed the Operational Data Science team.
Designed, implemented and maintained robust infrastructure and pipelines for massive data processing and analysis using Spark, GraphFrames, Oozie, Yarn and Zeppelin.
Increased ROI of marketing spend by 20%+ YOY by creating a bespoke marketing attribution system that tracks the conversion metrics of marketing at a granular level.
Designed, implemented and maintained robust infrastructure and pipelines for massive data processing and analysis using Spark, GraphFrames, Oozie, Yarn and Zeppelin.
Increased ROI of marketing spend by 20%+ YOY by creating a bespoke marketing attribution system that tracks the conversion metrics of marketing at a granular level.
Local Availability
Only available in these countries:
United Kingdom
I am based in the UK and am open to working remotely as well as traveling.
Other
Get in touch for a FREE consultation call before working together.
I have a passion for AI and transforming its research into impactful real-world applications. I am experienced in building scalable, fault-tolerant distributed systems that deal with large data volumes, having been programming for 20 years, including 9 with Python, 6 with the PyData stack, and 3 with Spark.
With data science, I have full-stack experience spanning the construction of robust ETL and data pipelines, and the development of associated visualization tools based on real-world data. In summary, I build data products, productionise data science solutions, and have extensive experience in the field of data engineering and machine learning.
Key Specialities: Machine Learning | Data Science | AWS | Python | SQL | Java | Jupyter | Spark | Data Engineering | Data Analysis | Research
I have a passion for AI and transforming its research into impactful real-world applications. I am experienced in building scalable, fault-tolerant distributed systems that deal with large data volumes, having been programming for 20 years, including 9 with Python, 6 with the PyData stack, and 3 with Spark.
With data science, I have full-stack experience spanning the construction of robust ETL and data pipelines, and the development of associated visualization tools based on real-world data. In summary, I build data products, productionise data science solutions, and have extensive experience in the field of data engineering and machine learning.
Key Specialities: Machine Learning | Data Science | AWS | Python | SQL | Java | Jupyter | Spark | Data Engineering | Data Analysis | Research
