Staff Software Engineer, Ads ML Inference Infrastructure

📋 Description

• Lead next-gen model inference and feature serving for 100x larger models.
• Design low-latency, high-throughput inference pipelines to meet SLOs.
• Collaborate to productionize new model architectures (LLMs, ranking) and scale globally.
• Evolve online feature platform for coverage, freshness, consistency.
• Evaluate GPU acceleration, model compression, Triton, vLLM, Dynamo.
• Partner with infra/ML teams to boost reliability and velocity.

🎯 Requirements

• BS degree in Computer Science or related field.
• ~8+ years designing/operating large-scale ML or distributed infra.
• Deep knowledge of Java, C++, Python.
• Distributed systems or ads infra (routing, storage, caching).
• Hands-on with PyTorch or TensorFlow.
• Proven track record leading complex projects and mentoring.

🎁 Benefits

• Hybrid work model; in-person 1-2 days per week near Palo Alto/SF/Seattle.
• PinFlex flexible working options and information page.