Senior ML Engineer: Real-Time Ad Ranking & Prediction

DT; New York (NY); Hybrid; USD 170,000 - 230,000; Full time

Job summary

Digital Turbine is seeking a Senior Machine Learning Engineer in New York to design and scale ML systems powering ad ranking, bid optimization, and user-level prediction across DSPs and content. You will build pipelines and serving infra turning data into measurable lifts.

You will collaborate with Data Science, Data Engineering, and product teams to ship models that move key metrics, run online experiments, and stay ahead with applied ML research.

Qualifications

• 8+ years building and deploying ML systems in production at scale.

Responsibilities

• Design, build, and deploy large-scale ML systems for ad ranking, click-through and conversion prediction, bid optimization, and next-best-action recommendation.
• Build and operate production ML pipelines - feature engineering, distributed training, deployment, retraining, and monitoring - that process billions of events and serve predictions at low latency.
• Leverage data assets from across the DT product portfolio to enable real time decisioning using the full feature set.
• Optimize training and inference for compute efficiency (CPU/GPU), latency, and cost across distributed systems.
• Partner with Data Science, Data Engineering, and product teams to ship models that move key business metrics and run online experiments to validate impact.
• Stay current with applied ML research and bring innovative techniques to advertising, ranking, and audience modeling.

Skills

ML systems

Python

Java/Scala/C++

PyTorch

TensorFlow

JAX

Distributed systems

Education

Master's or Ph.D. in CS/ML

Tools

PyTorch

TensorFlow

JAX

Spark

Beam/Dataflow

Flink

Job description

Digital Turbine is seeking a Senior Machine Learning Engineer in New York to design and scale ML systems powering ad ranking, bid optimization, and user-level prediction across DSPs and content. You will build pipelines and serving infra turning data into measurable lifts.

You will collaborate with Data Science, Data Engineering, and product teams to ship models that move key metrics, run online experiments, and stay ahead with applied ML research.