Advertising ML Engineer — Real-Time, Scalable AI

Mintegral; Seattle (WA); On-site; USD 120,000 - 170,000; Full time

Job summary

Mintegral in the United States seeks Machine Learning Engineers to develop and optimize large-scale ML models for advertising ranking, retrieval, and personalization. You will build production-grade ML solutions with PyTorch, and design scalable pipelines for training and inference in a modern distributed system.

The role emphasizes applying advanced ML techniques such as reinforcement learning and causal inference to improve advertiser outcomes and system efficiency, collaborating closely with

Qualifications

• Strong programming skills in compiled languages like C++ and modern Python.
• Solid foundation in algorithms, data structures, and distributed systems.
• Interest in ML systems, AI infrastructure, and high-performance computing.

Responsibilities

• Develop and optimize large-scale ML models for advertising ranking, retrieval, and recommendation.
• Build production-quality ML solutions using PyTorch and modern deep learning frameworks.
• Create scalable distributed training pipelines for large-scale models.
• Research reinforcement learning, causal inference, and optimization for advertising decisions.
• Explore RL approaches for real-time bidding, budget optimization, and sequential decision making.
• Design experiments to improve model performance, user experience, and advertiser outcomes.
• Collaborate with engineers to deploy ML models into production systems.

Skills

C++

Python

Java

Go

Education

Bachelor's/Master's/PhD in CS or related

Job description

Mintegral in the United States seeks Machine Learning Engineers to develop and optimize large-scale ML models for advertising ranking, retrieval, and personalization. You will build production-grade ML solutions with PyTorch, and design scalable pipelines for training and inference in a modern distributed system.

The role emphasizes applying advanced ML techniques such as reinforcement learning and causal inference to improve advertiser outcomes and system efficiency, collaborating closely with