Base Compute
basecompute.co
Actively hiring
Machine Learning
AI Compute & Inference
View 3 jobs
Follow
Overview
News
Technologies
Salaries
Products
People
Growth
Offices
Jobs
Financials
Funding and backers
Hiring now
3
open roles
Momentum
30/100
in the news, rising traction
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 20
Launched on Hacker News Show HN: Zero () friction local AI for Mac
Tractionpublic signals, read monthly
Investors in similar startupsfunds that back the companies most like this one
backs Featherless
Similar startupsby what they do, their industry and backers
OpenInfer is an innovation lab building one unified inference stack, from kernel to cloud — reimagining inference around the economics of…
Sail is the AI inference provider designed for agents at scale. Our API lets you deploy billions of tokens towards your hardest problems.
Munito is an open-model inference provider for Europe, private by default. Its API lets businesses choose their models and keep inference…
On-device AI with cloud fallback. Cactus post-trains models to know when they are wrong and hand off to frontier cloud models — cutting…
Tensormesh helps AI teams cut inference costs by caching and reusing repeated context. Run faster, lower-cost workloads with serverless and…
AI that keeps your data private at all times. Fast, powerful, and verifiable, thanks to secure hardware enclaves.
News
State of Local AI Report Base Compute
What runs locally in 2026: capabilities mapped to model classes, hardware tiers with realistic tokens/sec, memory math and speed thresholds for on-device AI.
Read more
Report
Local Private AI that runs on your Mac
Local is a macOS app that runs AI on your own machine. It tunes itself to your chip with BaseRT, so chat, coding and meeting notes run faster on the same hardware, without your work leaving the device.
Read more
Report
Get BaseRT Base Compute
BaseRT is the fastest LLM runtime on Apple Silicon. Install it with one command and run local models on your own device.
Read more
Report
Tech stack
Technologies named in job postings at Base Compute over the last 12 months, by layer, with the share of postings for each.
Technologies in use
15
Postings analysed
3
Stack modernity
66/100AI adopter
Languages
C++
Rust
Frameworks & libraries
CUDA
ROCm
Triton
Cloud & platforms
CUDA Toolkit
AI & ML
LLM
Sign in to see how your skills match this stack
Sign In
Full Base Compute tech stack
15 technologies · by team · pay by technology · changes · similar stacks
Growth
Hiring Momentum
58/100
Growing
Open positions
3
0 opened / 0 closed in 30 days
ATS activity
Every ~3 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.
AI/ML
100% ▼
Activity Timeline
Added Machine Learning to stack
Sep 2026
Added KV Cache to stack
Sep 2026
Added Speculative Decoding to stack
Sep 2026
Added Model Distillation to stack
Sep 2026
Added LLMOps to stack
Aug 2026
Added ROCm to stack
Aug 2026
Added Edge AI to stack
Aug 2026
Added Triton to stack
Aug 2026
Added CUDA to stack
Aug 2026
Offices
Where the company hires and what each office is for
Cities
2
Hiring now
2
Countries
2
Busiest office
Melbourne
Loading the map
Headquarters
Builds here
Office with open vacancies
Tap a pin for the office
Melbourne
Australia
2 open roles 100% engineering
hires for AI/ML
Berlin
Germany
1 open roles 1 posted in 90 days 100% engineering
hires for AI/ML
Jobs
≈ $71k – $164k per year (Estimated) • In office • Full-Time • PhD • Berlin
CUDA Toolkit
Reinforcement Learning
Quantization
LLM
CUDA
Triton
ROCm
Edge AI
Speculative Decoding
Model Distillation
Apply
In office • Full-Time • 3+ years exp • Melbourne
Rust
C++
CUDA Toolkit
Quantization
LLM
CUDA
Triton
LLMOps
ROCm
Edge AI
Speculative Decoding
KV Cache
Machine Learning
Apply
In office • Full-Time • PhD • Melbourne
CUDA Toolkit
Reinforcement Learning
Quantization
LLM
CUDA
Triton
ROCm
Edge AI
Speculative Decoding
Model Distillation
Apply