CoralBricks

Careers at CoralBricks

Build the fastest, most affordable inference for coding and research workflows.

The team is small, technical, and shipping.

Open roles

Our mission is to make frontier intelligence affordable and accessible to everyone.

  • Distributed Systems Engineer, GPU Infrastructure

    Engineering · San Francisco or remote · Full-time

    Own the production systems behind our GPU fleet: provision and operate clusters, build scheduling and deployment infrastructure, launch new models, and keep the platform reliable as it scales.

  • Inference Research Engineer (Member of Technical Staff)

    Research · San Francisco or remote · Full-time

    Research and build new ways to make LLM inference faster and more affordable: batching, scheduling, parallelism, quantization, and systems work measured against real agent workloads.

Don’t see your role?

Tell us what you'd want to work on and what you've built. We read every one.

[email protected] (Subject: Open Application)

Why we exist

Frontier models are finally here, but almost nobody can afford to use them freely. People have token anxiety: they meter every call, ration every context window, and settle for weaker models because the best ones are priced out of everyday use.

We're building the inference platform that ends that, starting with the workloads that feel the squeeze hardest: research and coding agents that swarm across multiple models, plan, call tools for hours, and reason over big context. Classic LLM serving was never built for them: rate limits that throttle real workloads, queues that stretch a 20-minute job into a 4-hour one, costs that grow with every agent turn. Same models, same prompts, but many times the tokens per second at a fraction of the cost.