AskBosco · ML engineering · Since 2024
MMMplatformandMLpipelinesfor AskBosco
Architected about 95% of the core marketing mix modelling system, with automated pipelines on Vertex AI.
~95%Of the core MMM system architected
01 / 03
Data in
Marketing and sales data land in the platform on a schedule.
02 / 03
Train and deploy
Vertex AI pipelines retrain the models and deploy them, the same way every time.
03 / 03
Watch it run
Monitoring keeps production models reliable and reproducible.
The project
- Client
- AskBosco
- Role
- Data Scientist, AskBosco
- When
- Since 2024
- Discipline
- ML engineering
- Tools
- Vertex AI
- GCP
- Python
- Git
- CI
The situation
Models only pay for themselves if they keep running: retrained, deployed and watched without someone doing it by hand.
What I built
- About 95% of the core MMM system inside AskBosco's analytics platform
- Automated ML pipelines in Vertex AI for training, deployment and monitoring
- Git-based version control for continuous development and integration
What changed
Production models that are reliable and reproducible, retrained and monitored automatically.
- ~95%Of the core MMM system architected
Hiring for marketing measurement or customer ML in the UK?
Eligible to work in the UK, no sponsorship needed. Based in London.
The CV is a two-page PDF, rebuilt from this site whenever it changes.
Jihar Gifari · London · jigifari@gmail.com · +44 7985 687426