Silicon & Systems Technical Product Manager

Positron AI is building next-generation AI inference accelerators for low-latency, high-throughput large language model inference. The Silicon & Systems Technical Product Manager will lead product planning for the silicon and systems product line, writing requirements, defining roadmaps and SKU strategies, analyzing performance and competition, and aligning engineering, go-to-market teams, partners, and customers.

Responsibilities:

• Serve as the leader at Positron AI for all aspects of silicon and systems technical product planning
• Write PRDs for our inference servers and inference rack systems, spanning silicon architecture, CPU and memory, through to rack scale system design
• Define and manage the product lifecycle and SKU strategy across generations
• Create scope and feasibility frameworks that convert advanced technology ideas and innovations into tangible, actionable engineering requests
• Partner with engineering and go-to-market teams to build and communicate a coherent product roadmap
• Work closely with go-to-market teams to understand customer and market needs, and translate them into product direction
• Own the decision history for the product line, acting as the documented answer to "why did we choose X," including with executive leadership
• Create and maintain competitive briefings covering the AI inference hardware landscape
• Engage key supply chain and technology partners to understand their technology roadmaps and factor them into our planning
• Ensure our hardware and systems products are thoroughly and accurately documented
• Streamline and automate product planning processes using agentic AI, scaling your own output through agent workflows

Requirements:

• 10+ years of experience across a strong mix of silicon and systems technical disciplines, as outlined below
• Deep expertise in silicon or systems engineering and architecture (AI accelerator, CPU/GPU, networking, or memory systems), with direct ownership of feature, PPA, or architecture trade-offs
• Hands-on experience with cloud scale server and computing systems deployments, including power and cooling envelopes, rack integration, networking, fleet-wide telemetry, and failure and RMA workflows
• Strong command of performance analysis spanning silicon and systems, including roofline modeling, bandwidth utilization, and $/GB and perf/W arithmetic, with the ability to build and defend the math personally
• Proven ability to move quickly between low-level silicon detail and rack scale system behavior, paired with a habit of staying current on the AI hardware landscape
• Excellent communication and interpersonal skills, with comfort navigating uncertainty and driving a deliberate process of idea and decision socialization
• Comfortable being the most technically grounded person in a go-to-market room and the most market-aware person in an engineering room
• Demonstrated daily, hands-on use of agentic AI in real technical work, including building and running agent workflows for research, analysis, and drafting requirements, with the judgment to verify and own everything the agents produce
• Direct experience with OEM and ODM needs, including reference designs, compliance, and hardware qualification cycles
• A background in AI inference systems competitive landscaping and analysis, either at an AI hardware startup or an incumbent AI hardware systems provider
• Prior experience defining SKU strategy and product lifecycle for a hardware platform sold into hyperscale or enterprise data center environments