Product Manager - AI Inference & Model Serving

Mirantis • Austin, TX

1d

About The Position

Mirantis is looking for a commercially driven, deeply technical Product Manager to own AI inference and model serving for k0rdent AI, our control plane for GPU infrastructure and distributed AI workloads. This role sits at the intersection of AI inference, cloud-native infrastructure, distributed systems, and performance engineering. You will define how NeoClouds and Enterprise customers deploy, scale, and operate production inference services while extracting maximum performance from the underlying GPU, network, and storage infrastructure. This role owns product strategy and solution development for inference products across on-premises, cloud, and edge environments. The scope includes serverless inference, dedicated endpoints, workload placement, autoscaling, routing, lifecycle management, observability, and full-stack performance optimization. This person will define how customers run production model-serving workloads at scale while improving latency, throughput, utilization, reliability, cost, and operational control. The ideal candidate has experience with high-performance infrastructure products and understands how production systems behave under real-world load. They should be comfortable reasoning across the full stack, identifying performance bottlenecks, evaluating system design trade-offs, and translating technical insight into clear product requirements, architecture direction, and customer-facing solutions.

Requirements

• 7+ years in product management, technical product management, or a senior technical role owning AI/ML and inference product(s)
• Strong understanding of production AI inference, including model serving, serverless execution, dedicated endpoints, autoscaling, routing, workload placement, observability, and reliability
• Proven capability to reason about performance trade-offs across GPU, network, storage, orchestration, and runtime layers, and to translate low-level technical capability into business value such as TTFT, throughput per GPU, and TCO
• Working knowledge of modern inference runtimes (vLLM, SGLang, TensorRT-LLM, Dynamo, Triton) and the optimization patterns that matter in production: continuous batching, KV cache management, cold starts, prefill versus decode, disaggregated serving, and multi-model serving
• Credibility with engineering leaders and infrastructure operators, including comfort in production architecture reviews and technical commercial conversations with platform engineering buyers

Responsibilities

• Own product strategy, roadmap, and lifecycle for inference and model serving, including serverless inference, dedicated endpoints, autoscaling, routing, KV cache management, and the related observability
• Lead deep technical discovery with NeoClouds, sovereign clouds, and enterprise platform teams, and translate findings into prioritized requirements and architecture direction
• Partner with engineering on system design trade-offs across runtime integration, GPU scheduling, network, storage, and serving topology, including disaggregated serving and multi-model serving
• Define positioning grounded in measurable outcomes: latency distributions, throughput per GPU, utilization, tail reliability, and cost per tokens
• Drive go-to-market execution: pricing and packaging, reference architectures, sizing guides, PoC playbooks, and direct engagement with customers, analysts, and ecosystem partners

Benefits

• Professional development and training.
• Attend conferences and working groups.
• Customized workstation (macOS, Windows).
• A competitive compensation package with strong benefits plan and stock options.

What This Job Offers

• Job Type: Full-time
• Career Level: Senior
• Education Level: No Education Listed