Positron develops inference-focused AI chips and systems for transformer workloads.
This slot renders the company's funding history: dates, rounds, amounts, valuations and lead investors once populated in data/funding-rounds.json.
Mitesh Agarwal argues Positron's architecture solves the HBM/CoWoS supply constraint by using commodity LPDDR5X memory, enabling faster scaling to hundreds of megawatts for hyperscaler customers.