Fireworks AI

About Fireworks AI

Fireworks AI is an inference-platform company — fast, cost-efficient serving of open-weights and proprietary language models for enterprises. Founded in 2022 by ex-Meta PyTorch leaders, Fireworks serves models like Llama, Mixtral, and Qwen at scale and ships fine-tuning, function-calling, and quantization tooling. Hiring is heavy on AI infrastructure (GPU kernels, inference servers, distributed systems), applied research (efficient inference, quantization), and customer-facing engineers. Fireworks is a top destination for engineers who want to work on the systems layer of generative AI and care about milliseconds and dollars per token.