Staff ML Engineer, Ads ML Infrastructure

What you'll do

• Design and develop secure, scalable back-end systems for high-performing machine learning platforms.
• Build and operate large-scale, low-latency ML serving platforms for real-time and batch inference.
• Implement model quantization, tensor parallelism, and inference optimizations using tools like ONNX Runtime or TensorRT.
• Develop distributed systems to support scalable inference workloads and hybrid online/offline serving patterns.
• Optimize low-level GPU kernels to maximize hardware utilization and accelerate deep learning primitives.
• Build foundational AI/ML infrastructure including Feature Stores and Vector Databases to improve model lifecycle management.
• Create developer tools, abstractions, and automation to streamline ML workflows and reduce operational burden.
• Mentor other engineers through code reviews, design leadership, and internal knowledge sharing.

What we're looking for

• Proven track record of designing and operating large-scale, low-latency ML Serving platforms for real-time and batch inference.
• Experience with model quantization, tensor parallelism, and inference optimizations using tools like ONNX Runtime, TensorRT, or vLLM.
• Experience working on distributed systems such as Ray and high-throughput RPC systems to support scalable workloads.
• Hands-on experience designing and optimizing low-level GPU kernels to maximize hardware utilization and accelerate deep learning primitives.
• Prior experience in the advertising industry, federated learning, and privacy-preserving ML techniques.
• Experience leading the development of foundational AI/ML platforms including Feature Stores and Vector Databases.
• Recognized technical leader capable of mentoring engineers through code reviews and knowledge sharing.
• PhD, MS, or BS in computer science or a related field with 8+ years of experience in machine learning and software engineering.