<h4>Why Kimchi?</h4> <p>Great models are raw ingredients.
Kimchi is what happens when you ferment them with good engineering.
We started inside CAST AI helping companies run LLMs on their own Kubernetes clusters; today we run our own coding harness on any model you pick, and we run the models underneath it ourselves.
<br><br><strong>Kimchi Inference</strong></p> <p>One API line and a customer's existing client just works: DeepSeek, GLM, Kimi, MiniMax, Nemotron served serverless from our own GPU fleet (OpenAI- and Anthropic-compatible, pay per token, spend visible per user, team, and key).
When control matters, the same models run on the customer's own cluster instead.
Behind that one line sits the machinery you'll own: SGLang and vLLM engines, B300 nodes, a shared cluster filesystem that holds every checkpoint exactly once, KV caches riding coding traffic with heavy prefix reuse, and the benchmark harness that gates every change we ship.
<br><br></p> <p><em data-prosemirror-content-type="mark" data-prosemirror-mark-name="em"><span id="edb2bdea-40e7-48f0-9485-a0bd7169c7c7" data-mark-type="annotation" data-mark-annotation-type="inlineComment" data-id="edb2bdea-40e7-48f0-9485-a0bd7169c7c7" data-prosemirror-content-type="mark" data-prosemirror-mark-name="annotation">Made by Cast AI — a Miami-headquartered, globally distributed team across 34 countries that hit unicorn status in January 2026 with a $50B+ backed investment pushing its valuation past $1 billion.
</span></em></p> <h4>.
Throughput
Cold starts.
Cost per token.
</p> <p>Move those four numbers in the right direction and two things happen: customers get faster, cheaper inference, and our margins improve.
That's the entire thesis of this role.
Every loader you tune, every scheduler decision you land, every kernel you stare at shows up in a customer's p99 and on our P&L.
Your mandate is the inference stack's optimization, whatever it takes, and the technical direction of how we op.