Job Description
Drive transformative innovation by building and scaling the data and AI feature infrastructure for AI-powered ranking, bidding and recommendation systems in digital advertising. Lead the design and implementation of high-performance data pipelines and feature stores that ensure data consistency, low latency, and reliability. As a technical leader, you will elevate our feature engineering and data delivery capabilities, enabling advanced modeling at scale and shaping the future of data-driven decision-making.
Core Skills & Expertise:
The ideal candidate will demonstrate:
1. Exceptional Data Engineering & Infrastructure Mastery:
2. Mastery in designing and building efficient data pipelines to feed AI ranking, bidding and recommendation systems.
3. Expertise in implementing and maintaining Feature Stores (online and offline) for fast and consistent feature serving to ML models.
4. Advanced knowledge of streaming data technologies (, Kafka, Pub/Sub) and large-scale data processing engines (, Spark, Flink) in a cloud environment (GCP/AWS).
5. Advertising Data Domain Knowledge:
In-depth understanding of AdTech data sources (eg bid request logs, server logs, front-end events) and the infrastructure required to process them.
Proven experience building data flows that support the feature engineering necessary to optimise CPC, CPA, and ROAS metrics for advertisers.
6. Exceptional Data Processing and System Expertise:
Advanced proficiency in Python (for building robust ETL/ELT) and SQL (for data modeling and warehousing).
Strong foundation in data modeling, schema design, and ensuring data quality/integrity for high-volume ML features.
Ability to design reliable, scalable systems that support complex feature transformations required for multi-objective optimisation models.
7. Proven Leadership in Data Systems:
A track record of designing and deploying high-performance data pipelines and feature infrastructure in production, with measurable stability and performance.
Experience influencing data architecture strategy and driving adoption of best practices for data consumption by Data Science teams.
A history of mentoring junior engineers and driving alignment on data infrastructure standards across engineering and data organizations.
Qualifications
Nice-to-Haves:
8. Deep MLOps and Infrastructure Experience: Expertise in managing and optimising feature serving infrastructure for low-latency requirements, including techniques like caching, sharding, and geographically distributed serving for high-volume prediction and decision services.
9. Feature Layering for Causal/Economic Models: Familiarity with the data requirements and pipeline design to support features for econometric models or causal inference (eg handling complex time-series lags, external shock data).
10. Cloud-Native Data Ecosystems: Certified expertise (or equivalent experience) in specific cloud-native data services (eg Google Cloud Dataflow, BigQuery, Vertex AI Feature Store, AWS Kinesis) that enable full operationalisation of the ML feature lifecycle.
11. Advanced ML Architecture Knowledge: Working knowledge of advanced ML architectures, such as Transformer-based models or Graph Neural Networks, to anticipate and design the necessary feature representations and data flows required by Data Scientists.