{"slug":"ai-asics","title":"AI ASICs","tagline":"Hyperscaler silicon: TPU, Trainium, MTIA, Maia — and the merchant gap they create.","hub_url":"/topic/ai-asics","counts":{"companies":6,"business_signals_90d":0,"talent_signals":0,"jobseeker_profiles":4,"fit_scores":0},"companies":[{"slug":"amd","name":"AMD","primary_layer":"L2","description":"MI300 / MI325 / MI350 Instinct accelerator family — the dominant merchant alternative to NVIDIA in AI training silicon. ROCm software stack maturity is the primary watch-point.","profile_url":"/companies/amd"},{"slug":"groq","name":"Groq","primary_layer":"L2","description":"LPU inference-only accelerator; deterministic-latency architecture. GroqCloud commercial inference service. Sample point for inference-specialised non-NVIDIA silicon path.","profile_url":"/companies/groq"},{"slug":"cerebras-systems","name":"Cerebras Systems","primary_layer":"L2","description":"Wafer-scale Engine — single-chip alternative to multi-chip GPU clusters. Filed for IPO in 2024 (deferred). Real production deployments in scientific / pharma + select hyperscaler inference.","profile_url":"/companies/cerebras-systems"},{"slug":"tenstorrent","name":"Tenstorrent","primary_layer":"L2","description":"Wormhole + Blackhole AI chips on RISC-V cores. Open-source software stack (TT-Metalium). Jim Keller-led architecture; named in multiple sovereign-AI government compute initiatives.","profile_url":"/companies/tenstorrent"},{"slug":"sambanova-systems","name":"SambaNova Systems","primary_layer":"L2","description":"Reconfigurable Dataflow Architecture (RDU) — appliance + cloud model. Strong enterprise + government deployments. Pivoted toward inference-of-large-models from training focus.","profile_url":"/companies/sambanova-systems"},{"slug":"rebellions-ai","name":"Rebellions","primary_layer":"L2","description":"Korean AI inference chip startup. Atom chip + REBEL roadmap. Merged with Sapeon (SK Telecom AI chip subsidiary) in 2024. Sovereign-Korea-AI angle on inference silicon.","profile_url":"/companies/rebellions-ai"}],"personas":[{"segment_id":"ASICS-ML-SYS-ENG-01","one_liner":"ML systems engineer evaluating merchant AI silicon (AMD / Groq / Cerebras / etc.) vs NVIDIA defaults.","url":"/topic/ai-asics/personas/ASICS-ML-SYS-ENG-01"},{"segment_id":"ASICS-PROCURE-LEAD-01","one_liner":"Procurement / supply-chain lead negotiating accelerator allocation at large AI buyer.","url":"/topic/ai-asics/personas/ASICS-PROCURE-LEAD-01"},{"segment_id":"ASICS-RESEARCH-SCI-01","one_liner":"Research scientist running benchmarks on merchant AI accelerators for publication / internal eval.","url":"/topic/ai-asics/personas/ASICS-RESEARCH-SCI-01"},{"segment_id":"ASICS-SOVEREIGN-LEAD-01","one_liner":"Sovereign-AI program lead at national-government / research-council level.","url":"/topic/ai-asics/personas/ASICS-SOVEREIGN-LEAD-01"}],"generated_at":"2026-05-14T16:50:51.148Z"}