Senior ML Engineer - AdTech (Real-Time Bidding)

Roku; Cambridge; Hybrid; GBP 90,000 - 130,000; Full time

Job summary

Roku is seeking a senior ML engineer to join Praveen Krishnaiah’s Native Ads Modelling team in the UK, building ML systems from idea to serving at scale using Spark, Python and Java. You’ll work on ad relevance, bid optimization and real-time inference.

You’ll design, train and deploy production ML infrastructure for real-time, low-latency serving and collaborate with the Ad Performance ML team to deliver impactful results, while applying rigorous evaluation and feature engineering practices.

Qualifications

• Senior ML engineering experience, ideally with exposure to ad tech, recommendation, or auction systems.
• Strong grounding in ML fundamentals, feature engineering, and model evaluation.
• Experience with Spark, Python, and Java in production ML settings.
• Comfort with production ML infrastructure and real-time, low-latency serving requirements.
• Demonstrated AI/agentic-tooling fluency per the section above.
• Clear communicator who can explain reasoning and trade-offs, not just conclusions

Responsibilities

• Design, train, and ship ML models for ad relevance and bid/yield optimization
• Build and maintain production ML infrastructure for real-time, low-latency serving
• Work across Spark, Python, and Java to move models from research to production
• Apply sound feature engineering, validation, and evaluation practices throughout the modelling lifecycle
• Diagnose production ML issues such as model drift or long-tail classification problems
• Communicate technical trade-offs clearly to engineering and cross-functional partners

Skills

Senior ML engineering

ML fundamentals

Feature engineering

Production ML systems

Spark

Python

Java

Tools

Spark

Python

Java

Job description

Roku is seeking a senior ML engineer to join Praveen Krishnaiah’s Native Ads Modelling team in the UK, building ML systems from idea to serving at scale using Spark, Python and Java. You’ll work on ad relevance, bid optimization and real-time inference.

You’ll design, train and deploy production ML infrastructure for real-time, low-latency serving and collaborate with the Ad Performance ML team to deliver impactful results, while applying rigorous evaluation and feature engineering practices.