Senior Machine Learning Systems Engineer (Ads Infrastructure)

About Us

Mintegral is a leading programmatic and interactive mobile advertising platform, starting from the APAC region and radiating out globally. Powered by advanced AI technology, we provide global advertisers and developers with innovative, comprehensive experiences. With our efficient mobile marketing and monetization solutions, we help our clients exceed their marketing goals.

As Mobvista’s self-developed programmatic platform, since Launched in 2015, Mintegral has quickly grown to become one of the largest mobile advertising platform in Asia. We offer a full stack of programmatic products and services including our Self-service Platform, DSP, SSP, Ad Exchange and DMP. We have also created the Mindworks Creative Studio, which offers publishers and brands cutting-edge creative solutions, from traditional creative right through to the latest interactive ad formats. For more information, please visit our website: https://www.mintegral.com/en/

About the Role

We are seeking a Senior Machine Learning Systems Engineer to architect and scale next-generation advertising ranking and serving infrastructure.

You will build large-scale real-time ML inference systems powering ad ranking, retrieval, and prediction across global traffic, focusing on distributed systems, ML infrastructure, and high-performance computing.

Responsibilities

• Design end-to-end ads ranking and serving architectures for real-time bidding and recommendation systems
• Build decoupled and disaggregated inference pipelines across CPU and GPU layers
• Optimize latency for high-QPS ad delivery systems

• Develop and optimize ML deployment pipelines for heterogeneous CPU/GPU environments
• Improve model freshness and inference performance
• Enable rapid iteration of ML models in production

• Design large-scale embedding storage and retrieval systems
• Build adaptive sharding strategies across heterogeneous hardware
• Improve load balancing and system stability

• Optimize QPS, latency, and throughput
• Identify bottlenecks in inference pipelines
• Improve end-to-end ranking performance

• Build AOT compilation frameworks for ML models
• Translate models into optimized C++/CUDA/ROCm execution
• Improve inference efficiency across hardware backends

• Work with engineers, and product teams
• Productionize ML models
• Define scalability and reliability standards

Required Qualifications

• 4+ years in distributed systems or ML infrastructure
• Experience in ML serving or recommendation systems
• Strong distributed systems and performance optimization background
• Experience with CPU/GPU systems
• C++ / Python proficiency
• ML frameworks experience

Preferred Qualifications

• Ads tech or recommendation systems experience
• ML compiler or inference runtime experience
• GPU optimization (CUDA/ROCm)
• High-scale system experience
• High-level ownership experience

Impact

• Enable large-scale real-time ads ranking
• Improve inference efficiency and cost
• Accelerate ML deployment cycles
• Build foundational ads infrastructure