echoloc
Get started
echoloc/ Companies/ Tenstorrent

Tenstorrent Tech Stack

AI-focused hardware design using RISC-V, from RTL to silicon

Computer Hardware Manufacturing Toronto, ON 501–1,000 employees Founded 2016 Privately Held
tenstorrent.com LinkedIn

Tenstorrent designs custom silicon for AI workloads, with engineering-led R&D spanning CPU cores, compilers, and verification infrastructure. The stack reveals a full-stack hardware company: RISC-V ISA, high-level synthesis (MLIR), simulation (Gem5, VCS), physical design (Innovus, RedHawk), and ML frameworks (PyTorch, JAX, TensorFlow). Active projects span CPU RTL, a custom compiler (tt-forge), chiplet architecture, and customer silicon bring-up — indicating movement from internal design toward production deployment.

Tech Stack 153 technologies

Core StackC++ Python PyTorch TensorFlow RISC-V x86 ARM NVIDIA GPU Ubuntu Red Hat Enterprise Linux CentOS Verilog VHDL UVM FPGA SystemVerilog JAX MLIR Innovus RedHawk Tcl Perl Synopsys VCS JTAG FinFET Gem5 Visual Studio Code TCL SPICE Bash+122 more
AdoptingRISC-V

What Tenstorrent Is Building

◆Challenges

  • Optimizing model performance
  • Improving development efficiency
  • Debugging complex verification flows
  • Optimizing ppa and runtime efficiency
  • Complex physical design challenges
  • Optimizing eda tools
  • Coverage gaps
  • Supporting risc-v certification
  • Scaling verification across large cpu programs
  • Ensuring manufacturable silicon across advanced nodes

▲Active Projects

  • Cpu core functional verification
  • Tt-explorer
  • Cpu core-level test generator development for high-performance out-of-order risc-v cores
  • Open chiplet architecture
  • Rtl design environment enhancement
  • Coverage model development
  • Tt-forge compiler development
  • Cpu system rtl implementation
  • Model performance tuning on custom silicon
  • Customer silicon bring-up

Hiring Activity

Accelerating140 roles · 70 in 30d

Department

Engineering
122
Finance
3
HR
2
Logistics
2
Sales
2
Support
1

Seniority

Senior
63
Staff
27
Mid
22
Lead
12
Manager
4
Director
3
Principal
1

Notable leadership hires: Power Characterization Lead, System IP Lead

Company intelligence

Find more companies like Tenstorrent by tech stack, pain points and active projects

Get started free

About Tenstorrent

Tenstorrent builds custom processors for AI inference and training, targeting the gap between general-purpose CPUs and specialized accelerators. The company operates across the full hardware design stack: architecture definition, RTL implementation, functional verification, EDA optimization, and post-silicon validation. With 137 open roles concentrated in engineering (mostly senior and staff levels), the organization is scaled for complex chip design and compiler development. Offices span North America, Europe, Asia, and India, matching both hardware supply chains and AI research talent pools.

HeadquartersToronto, ON
Company Size501–1,000 employees
Founded2016
Hiring MarketsUnited States, Japan, Canada, India, Syria, Cyprus, Poland, Germany

Frequently Asked Questions

What is Tenstorrent's tech stack?

RISC-V, x86, ARM, NVIDIA GPU support, Python/C++, PyTorch/JAX/TensorFlow, MLIR, Verilog/SystemVerilog, Synopsys VCS, Innovus, Gem5, FPGA tools (UVM, JTAG), and physical design (FinFET, RedHawk, SPICE).

Where does Tenstorrent have offices?

Headquarters in Toronto. Global offices in Austin TX, Silicon Valley, Belgrade, Seoul, Tokyo, and Bangalore. Active hiring across US, Canada, Japan, India, Germany, Poland, Serbia, Taiwan, and Cyprus.

How this profile is built

Tenstorrent's technology stack, projects, and hiring signals are inferred from public hiring and company data — career pages, public listings, and company web presence — then clustered and de-duplicated. Figures are estimates that refresh over time. Read our full methodology →

This is not an official vendor or customer list. It is a technology-adoption signal inferred from public data, intended for B2B research.