DECODE
decode.agency
Actively hiring
Mobile App Development Services
Custom Software Development
As featured in
View 2 jobs
Follow
Overview
News
Salaries
Products
People
Growth
Offices
Jobs
Financials
How DECODE hires
Truth index
B 75/100
Ghost roles
0%
Stale roles
100%
Reposted roles
0%
DECODE scores B on the Alion truth index (A is best, E worst), measured over 3 open roles re-checked against its own hiring board: 0% look like ghost listings, 100% 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
News
AI labs need to start funding historical research
Using GPT-6 and Opus 5.5 to trace alchemical knowledge and decode 17th century letters
Read more
Report
NASA's PRIMA telescope has one big mission:
NASA has announced the advancement of its PRIMA telescope to the next stage with a significant mission to explore and decode the history and evolution of the Universe. The space telescope is the...
Read more
Report
AI is starting to decode animal language, and what it is finding is surprising
New AI models can identify communication patterns in ravens, generate real-time exchanges with songbirds and analyze sperm whale calls, but researchers warn that sound alone cannot reveal meaning and that talking back could carry serious risks
Read more
Report
Prefill on NVIDIA, Decode on AMD? 'Heterogeneous GPU Inference' with vLLM Appears in MLPerfあまぐり
When it comes to GPUs for running LLMs,should you stick with NVIDIA?Should you stick with AMD?That is the kind of choice one tends to imagine.However, on September 21, 2026, Cisco unveiled a rather interesting configuration.Using NVIDIA H200s and AMD Inst
Read more
Report
Thinking about Local LLMs Day 13 Reading 1 token takes 0.88ms, writing takes 87.5ms - Measuring the 100x difference between prefill and decode with a custom inference engineMindOrbit AI@Claudeを使った自動ブログ運営
Even if you paste a long prompt, you only have to wait for the first moment. After that, the text flows out slowly. This asymmetry is not just your imagination; it is because LLM inference is divided into two processes with completely different characteri
Read more
Report
Report
Original Transformer vs DeepSeek by Peter Gostev on Whip
Explore the original Transformer and DeepSeek V4.1 Flash, or take a one-minute visual tour of what changed.
Read more
Report
Adidas Barreda Decode sneakers are on clearance for only $32 at Nordstrom Rack - but selling fast
Nordstrom Rack has the popular Adidas Barreda Decode sneaker on sale for so cheap, you can actually grab a pair for just $32.
Read more
Report
The MLA decode speedup hiding in your model card
Naive MLA is an order of magnitude slower than MHA at long context. The fix is one matrix identity and almost nobody writes it the first time.
Read more
Report
Prefill vs. decode in LLM inference
Understand how prefill and decode shape time to first token, streaming performance, KV-cache pressure, and LLM serving decisions.
Read more
Report
Show more news
Growth
Hiring Momentum
62/100
Growing
Open positions
7
2 opened / 0 closed in 30 days
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.
Sales
100%
Offices
Where the company hires and what each office is for
Cities
2
Hiring now
1
Countries
2
Busiest office
Zagreb
Loading the map
Headquarters
Builds here
Office with open vacancies
No open vacancies right now Tap a pin for the office
Düsseldorf
Germany
HQ
We're a full-service partner to the world's most ambitious companies — Let's talk →
Plaza Cubes, Hammer Straße 19, 40219 Düsseldorf
Zagreb
Croatia
Regional office Registered seat
5 open roles 1 posted in 90 days 40% engineering 50-200 est. staff
hires for Backend, Sales, Early Careers
Jobs
≈ $30k – $88k per year (Estimated) • In office • Freelance • Zagreb
Apply
Apply