Job Description

About us n

n
- n

We're building a new category of interactive entertainment powered by AI characters, image, video, and real-time experiences. We’re one of the most-visited AI products globally, serving millions of users every day.

n
- n

We work in-person in Sydney, Australia, and hire globally.

n

How we work n

n
- n

User-first: We build what people want. We invest time to understand our users and focus on adding value instead of extracting value.

n
- n

High agency, high ownership: We own outcomes end-to-end. When something goes wrong, we take responsibility and fix it.

n
- n

Urgency: We prioritize ruthlessly, increase leverage, and move at an exceptional pace.

n

What you'll do n

n
- n

You'll own our model inference stack end-to-end — serving our in-house and open-source models to tens of millions of users at low latency and high throughput, and squeezing every bit of performance out of our GPU fleet.

n

Example projects n

n
- n

Ship a high-throughput inference server for our in-house models, serving millions of generations per day at <200ms latency.

n
- n

Squeeze more out of every GPU with batching, quantization, and custom CUDA kernels .

n
- n

Test and productionize LoRAs and our in-house models to serve 10s of millions of users.

n

What you'll bring n

n
- n

5+ years of experience building software at scale, with a focus on ML inference or GPU-accelerated systems .

n
- n

Deep familiarity with GPU inference : batching, quantization, and serving frameworks like vLLM, TensorRT, or Triton.

n
- n

The ability to get shit done end-to-end .



From understanding users → proposing an idea → implementation → iteration.

n
- n

Hunger to win. This is not going to be easy.

n

What we offer n

n
- n

Top-of-market compensation with meaningful equity upside.

n
- n

Real ownership from day one. Work on important problems and see the impact of what you ship.

n
- n

Fast-growing scope. As your impact grows, your responsibility and compensation should grow with it.

n
- n

A company card for food, coffee, tools, and anything that helps you do your best work.

n
- n

Daily team lunch and dinner at the office.

n
- n

An unlimited workspace budget to build your ideal setup.

n
- n

Visa sponsorship and relocation assistance for people moving to Sydney.

n

How we think about comp n

We raise the ceiling for exceptional performers , not the floor. As your impact grows, your compensation should too.

n

n
- n

The listed range is cash + equity, with superannuation on top.

n
- n

We review compensation every 6 months.

n
- n

Bonuses reward past impact, and raises reflect your new level.

n

Our interview process n

n
1. n

Intro call: 15 minutes to align on the role and company.

n
2. n

Founder interview: go deep on what you’ve built, how you think, and how you work.

n
3. n

Technical interview: 1 hour of system design and technical discussion. No live coding.

n
4. n

Paid work trial: spend 3 days with us in Sydney working on a real problem. We cover travel and accommodation, if needed.

n
5. n

Offer: if it’s a solid fit, we move quickly.

n

📌 Software Engineer (Model Inference) (New South Wales)
🏢 coreflow
📍 New South Wales