Tensordyne
tensordyne.ai
Actively hiring
AI Compute & Inference
AI Chips & Accelerators
Processors, MCUs & AI Chips
As featured in
View 17 jobs
Follow
Overview
News
Technologies
Salaries
Products
People
Growth
Offices
Jobs
Financials
Funding and backers
Team
201-500
employees, estimated range
Hiring now
19
+6 posted in 30 days
Backers
6
Plug and Play, Premji Invest
Momentum
38/100
hiring for its size, a new city, in the news
Last sign of life
this month
a posting or a news item
The story so fareach stage dated by its source: the company's releases, the press, registers, filings
Aug 10
First role in Germany Jr Software Engineer - ML Runtime - Rust
Nov 19, 2025
Launched on Hacker News Show HN: Token Economics Calculator for AI inference hardware
2017
Founded
Tractionpublic signals, read monthly
Web presence
top 5%
of 133.2M domains by links, Common Crawl
Registers and programsofficial lists and records that name the company
| Legal entity | Tensordyne GmbH | its site |
Backed byfrom the funds' portfolios and accelerator catalogs
Plug and Play 
Premji Invest 
BMW i Ventures 
Greatpoint Investment Management, LLC 
Mayfield 
Toyota Ventures Investors in similar startupsfunds that back the companies most like this one
Similar startupsby what they do, their industry and backers
d-Matrix is a semiconductor technology company based in Santa Clara, California, and was founded in 2019. The company develops specialized…
Velaura AI, Inc., formerly Auradine, builds ultra-low-power compute solutions for data center, edge, and physical AI applications.
Rebellions is a South Korean semiconductor company founded in 2020 by former Wall Street quantitative engineers and IBM chip designers to…
NeuReality is an Israeli company founded in 2019 that designs AI inference infrastructure. Its server-on-chip architecture removes CPU…
Groq is an American semiconductor company founded in 2016 by former Google engineers who had worked on the Tensor Processing Unit. It…
Fractile is a London semiconductor company founded in 2022 that designs chips for large language model inference. Its in-memory computing…
How Tensordyne hires
Truth index
A 87/100
Ghost roles
21%
Stale roles
0%
Reposted roles
0%
Tensordyne scores A on the Alion truth index (A is best, E worst), measured over 19 open roles re-checked against its own hiring board: 21% look like ghost listings, 0% have gone stale and 0% are the same role posted again. It measures how much of what this employer publishes turns into a real, finite search - not the employer as a workplace. How the index is computed
Overview
Tensordyne is an artificial intelligence infrastructure company headquartered in Sunnyvale, California, and founded in 2017. The company develops high-performance AI inference systems, including the Napier processor and Scorpio silicon, which utilize a proprietary logarithmic number system to reduce power consumption and increase processing speed. It operates as a fabless semiconductor firm serving data centers, hyperscalers, and neocloud providers with hardware and software solutions optimized for large-scale generative AI workloads.
News
Tensordyne Napier: What If One Rack Could Do the Work of Nine?
Inspired by a 400-year-old invention and built from the math up. Learn what really matters in designing a datacenter-scale AI inference system.
Read more
Report
Tensordyne makes a big bet on log math to beat Nvidia
Who needs compute-hungry multiplications when you can just add logarithms
Read more
Report
Tensordyne Converts AI Matrix Math To Logs To Crank Up Inference Oomph
Right off the bat, let's give a shout out to the mathematician propeller-heads who create the transf ...
Read more
Report
Tensordyne Napier AI Processor Announced with Logarithmic Math
Tensordyne Napier is a new AI accelerator targeting the math behind AI inference and its own 72 accelerator architecture
Read more
Report
Tensordyne's 3nm Napier AI Chip Promises 13x Higher Token Throughput Than Blackwell & Blazes Past Rubin With 1000 Tokens/s In Multi-Trillion Parameter Models
Tensordyne's Napier chip boasts 17x more tokens per watt & 13x higher throughput than NVIDIA Blackwell, revolutionizing AI inference systems.
Read more
Report
Tensordyne's Wild Log Math Aims to Leave Nvidia's AI Chips In the Dust
The startup uses logarithmic math to speed up inference
Read more
Report
Tensordyne Revives Logarithmic Math In A Bid To Cut AI Power Use
Tensordyne says logarithmic computing could reduce AI inference costs and power demands, offering an alternative to conventional chip designs.
Read more
Report
Show more news
Tech stack
Technologies named in job postings at Tensordyne over the last 12 months, by layer, with the share of postings for each.
Technologies in use
44
Postings analysed
18
Stack modernity
81/100AI adopter
Languages
Python61%
C++44%
Rust22%
Perl17%
Frameworks & libraries
PyTorch17%
SGLang11%
UVM11%
Triton6%
Databases
MySQL6%
Cloud & platforms
Linux17%
vLLM11%
AWS6%
Kubernetes6%
AI & ML
LLM28%
Qwen11%
DeepSeek6%
Llama6%
Sign in to see how your skills match this stack
Sign In
Full Tensordyne tech stack
44 technologies · by team · pay by technology · changes · similar stacks
Growth
Hiring Momentum
77/100
Scaling fast
Open positions
19
6 opened / 2 closed in 30 days
Median time-to-fill
214 days
faster than 8% of the market
ATS activity
Every ~4 hours
Today
Hiring Dynamics
+100%
Hiring Focus
The percentage next to each role is its share of the company's job openings over the last 90 days; the arrow shows the shift versus the previous period.
Hardware
33% ▼
Solutions
22% ▲
AI/ML
11% ▼
HR
11% ▲
Industrial Engineering
11% ▲
Early Careers
11% ▲
Activity Timeline
New location: San Jose
Oct 2026
Added VLM to stack
Oct 2026
Added Qwen to stack
Oct 2026
Added Llama to stack
Oct 2026
Added Kubernetes to stack
Oct 2026
Added Diffusion Models to stack
Oct 2026
Added DeepSeek to stack
Oct 2026
Added Cursor to stack
Oct 2026
Added Claude Code to stack
Oct 2026
Added Synopsys PrimeTime to stack
Oct 2026
Added vLLM to stack
Sep 2026
Added Triton to stack
Sep 2026
Offices
Where the company hires and what each office is for
Cities
3
Hiring now
3
Countries
2
Busiest office
Sunnyvale
Loading the map
Headquarters
Builds here
Office with open vacancies
Tap a pin for the office
Sunnyvale
United States
HQ
USA
17 open roles 5 posted in 90 days 76% engineering 50-200 est. staff
hires for Hardware, DevOps, Product
Sunnyvale, CA 94089
San Jose
United States
Engineering / R&D
Sunnyvale
17 open roles 5 posted in 90 days 76% engineering 50-200 est. staff
hires for Hardware, DevOps, Product
Munich
Germany
Engineering / R&D
Sunnyvale
2 open roles 4 posted in 90 days 50% engineering 10-50 est. staff
hires for Hardware, Solutions
Jobs
≈ $132k – $242k per year (Estimated) • In office • 10+ years exp • Bachelor's Degree • Sunnyvale • San Jose
Multimodal AI
DevOps
HPC
Management
Agile
Apply
≈ $186k – $372k per year (Estimated) • In office • Sunnyvale • San Jose
vLLM
Quantization
Multimodal AI
SGLang
PyTorch
LLM
Triton
KV Cache
Apply
≈ $77k – $159k per year (Estimated) • In office • Munich
Python
Rust
Cursor
Qwen
DeepSeek
Claude Code
vLLM
Quantization
Diffusion Models
VLM
SGLang
Llama
PyTorch
LLM
Mixture of Experts
KV Cache
DevOps
Kubernetes
Apply
≈ $124k – $241k per year (Estimated) • In office • 5+ years exp • Bachelor's Degree • Sunnyvale • San Jose
Python
Rust
C++
Bash
Multimodal AI
DevOps
RTOS
Linux
Apply
≈ $115k – $256k per year (Estimated) • In office • Bachelor's Degree • Sunnyvale • San Jose
Python
Rust
C++
Multimodal AI
InfiniBand
DevOps
CI/CD
HPC
Linux
BGP
Apply
≈ $165k – $298k per year (Estimated) • In office • 10+ years exp • Bachelor's Degree • Sunnyvale • San Jose
Multimodal AI
DevOps
HPC
Chips/EDA
Synopsys PrimeTime
Management
Agile
Apply
≈ $64k – $149k per year (Estimated) • In office • 3+ years exp • Bachelor's Degree • Munich
Python
C++
SystemC
Multimodal AI
Apply
≈ $196k – $374k per year (Estimated) • In office • Bachelor's Degree • Sunnyvale • San Jose
Multimodal AI
AI Agents
Mixture of Experts
World Models
Apply
≈ $107k – $207k per year (Estimated) • In office • 3+ years exp • Master's Degree • Sunnyvale • San Jose
Verilog
SystemVerilog
Multimodal AI
Web3
Tokenomics
Apply
≈ $166k – $300k per year (Estimated) • In office • 10+ years exp • Master's Degree • Sunnyvale • San Jose
Verilog
SystemVerilog
Multimodal AI
Web3
Tokenomics
Apply
≈ $160k – $303k per year (Estimated) • In office • 15+ years exp • Master's Degree • Sunnyvale • San Jose
Python
Verilog
C++
Perl
SystemC
Multimodal AI
TPU
DevOps
HPC
Apply
≈ $162k – $292k per year (Estimated) • In office • 15+ years exp • Master's Degree • Sunnyvale • San Jose
Python
C++
SystemVerilog
Perl
Multimodal AI
Computer Vision
Chips/EDA
UVM
Apply