Senior Product Manager, AI Inference - Dynamo (AI)

TL;DR

Senior Product Manager, AI Inference - Dynamo (AI): Define and drive product strategy for high-performance inference framework powering LLM and generative AI workloads at massive scale with an accent on routing, caching, and memory optimization. Focus on hardware-software co-design, agentic inference capabilities, and translating system improvements into business outcomes like reduced latency and cost.

Location: Remote (US)

Salary: $208,000 – $327,750 USD

What you will do

• Define and own product strategy and roadmap for distributed AI inference systems
• Drive intelligent routing, KV cache management, and multi-tier caching for LLM serving
• Collaborate on hardware-software co-design and develop PRDs for engineering execution
• Define agentic inference features and partner with ecosystem for framework integration
• Engage customers to incorporate real-world evaluations and monitor industry trends

Requirements

• 12+ years in product management, technical leadership, or engineering/product roles in AI/infrastructure
• Strong background in AI inference, distributed computing, GPU platforms, and LLM workflows
• Experience with large-scale serving systems, performance optimization, and MLOps
• Technical fluency to collaborate with research/engineering in matrixed environments
• Analytical, data-driven skills and customer-focused mindset for business impact

Nice to have

• Familiarity with agentic AI frameworks or generative AI systems
• Hands-on AI/ML background including research application

Culture & Benefits

• Equity participation and competitive base salary
• Comprehensive health, dental, vision insurance
• Focus on employee/family wellbeing
• Access to cutting-edge AI infrastructure and world-class teams
• Inclusive, innovation-driven culture in accelerated computing