Software Engineer (Model Inference)

• 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.

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

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

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

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

• →

  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.

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

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

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

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

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

• The ability to get shit done end-to-end. From understanding users → proposing an idea → implementation → iteration.

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

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

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

• We review compensation every 6 months.

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

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

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

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

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

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