Product Manager - AI Inference & Model Serving

📋 Description

• Own strategy, roadmap, and lifecycle for inference and model serving
• Define serverless inference, dedicated endpoints, autoscaling, and routing
• Manage KV cache and observability for production inference workloads
• Collaborate with NeoClouds and enterprise teams on requirements and architecture
• Align latency, throughput, utilization, and cost with measurable outcomes

🎯 Requirements

• 7+ years in product management or senior technical AI/ML roles
• Strong knowledge of production AI inference: model serving, autoscaling, observability
• Able to reason about GPU, network, storage, orchestration trade-offs
• Experience with runtimes: vLLM, SGLang, TensorRT-LLM, Dynamo, Triton
• Comfortable in architecture reviews and technical-commercial discussions with platform teams

🎁 Benefits

• Work with an established Silicon Valley leader in cloud infrastructure
• Collaborate with passionate colleagues across Fortune 500 and Global 2000 customers
• Be part of cutting-edge, open-source innovation
• Thrive in a high-energy environment with openness, collaboration, risk-taking, and growth
• Professional development and training
• Attend conferences and working groups