Product Manager, Hardware
Job Description
Normal Computing Corporation is building silicon for LLM inference, and the Hardware Product Manager role sits at the center of turning real-world workload needs into a chip roadmap that can make tapeout. You will translate constraints from customers and the supply chain into an actionable chip definition, then drive milestone ownership across architecture, RTL, verification, physical design, and signoff.
What you’ll do
- Shape the silicon roadmap, defining what goes into the chip and the execution plan that takes it through tapeout.
- Convert target workloads, customer signals, and supply chain constraints into a committed chip definition.
- Own milestones from architecture specification through RTL, verification, physical design, and tapeout signoff.
- Partner with the Head of Product to build cross-team alignment by explaining, in technical terms, how the silicon roadmap supports the company’s higher level product vision in discussions with the CPO, CTO, and CSO.
- Work with Silicon engineering to decide what is included in each silicon generation.
- Prioritize features based on target workloads, PPA tradeoffs, and what customers are likely to pay for.
- Coordinate with Ecosystem and Partnerships to translate workload assumptions and customer requirements into architecture requirements and success criteria for the design team.
- Own the end-to-end milestone plan from spec through tapeout.
- Track the dependency chain across architecture, RTL, verification, DFT, and physical design closure.
- Organize and facilitate milestone alignment and refinement meetings for internal stakeholders and external customers.
What you bring
- A degree in EE, CS, Material Science/Engineering, or similar, or the equivalent knowledge taught to yourself.
- 4+ years in product management, program management, or engineering roles in semiconductors or adjacent hardware.
- Experience closely connected to a tapeout, with understanding of the full lifecycle from spec through RTL, verification, physical design, DFT, and silicon bring-up.
- Practical fluency with coding agents, using tools such as Claude Code, Codex, Cursor, or similar as part of day-to-day work.
- Clear communication in both speaking and writing.
- Comfort operating in ambiguity, including the ability to frame a vague problem and return with a workable proposal.
Bonus points
- Experience defining or shipping AI accelerators, or deep familiarity with mechanisms underlying LLM inference.
- Exposure to SystemVerilog, design verification, or hardware performance modeling.
- Experience working directly with foundries or memory vendors.
- Understanding of ASIC-based inference server design, IP blocks, packaging, and how process node choices affect outcomes.
Location: New York, NY (onsite)
Salary: USD 200,000 - 250,000 per year
Minimum experience: 4 years