Software Engineer

About the Role

Software Engineer – Ads AI Infrastructure

Key Responsibilities

• Design and build high-performance AI infrastructure supporting large-scale advertising machine learning systems.
• Develop GPU-accelerated machine learning training and inference infrastructure, including distributed training, mixed precision training, and large-scale model optimization.
• Build and optimize ML systems using modern frameworks and technologies such as PyTorch, TorchRec, and distributed training frameworks.
• Design and implement high-throughput, low-latency real-time decision systems serving massive volumes of advertising requests.
• Build efficient data and feature pipelines supporting large-scale embeddings, multimodal features, and real-time feature serving.
• Develop scalable model serving infrastructure for production machine learning applications.
• Optimize system performance through parallel computing, GPU acceleration, memory optimization, and advanced system design.
• Collaborate closely with machine learning engineers and researchers to productionize state-of-the-art models.
• Build reliable, scalable, and maintainable infrastructure for next-generation advertising AI systems.

Requirements & Tech Stack

• Bachelor's, Master's, or Ph.D. degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, Mathematics, Statistics, Operations Research, or related fields.
• Strong programming skills in C++, Python, Java, Go, or similar languages.
• Strong foundation in algorithms, data structures, operating systems, distributed systems, and computer architecture.
• Strong interest in machine learning systems, AI infrastructure, and high-performance computing.
• Ability to solve complex engineering problems and quickly learn new technologies.
• Familiarity with PyTorch distributed training, TorchRec, DeepSpeed, FSDP, model parallelism, data parallelism, or 2D parallel training strategies is preferred.
• Experience with GPU programming (CUDA), high-performance computing, or system-level performance optimization is preferred.
• Experience with machine learning systems (ML Systems), large-scale AI infrastructure, or distributed training platforms is preferred.
• Experience building large-scale machine learning infrastructure, including training platforms, model serving systems, feature platforms, or embedding serving systems is preferred.
• Experience with real-time inference systems, low-latency services, or large-scale data processing is preferred.
• Research projects, internships, or open-source contributions related to AI infrastructure are highly valued.
• Strong research ability and problem-solving skills.
• Passion for online advertising, recommendation systems, and intelligent decision-making.