LLM Infrastructure EngineerFireworks AI
Our team at Fireworks AI 🎆 is hiring a Software Engineer (LLM Infrastructure) to work alongside Alan Chu and me!
We’re building the fastest, most reliable gen AI platform on the market, and we need an engineer who is deep in the weeds of open-source systems, custom fine-tuning, and model serving.
Who we’re looking for: You don’t just use high-level wrapper APIs—you understand core LLM mechanics (disaggregated prefill, KV cache memory limits, system bottlenecks) and love getting your hands dirty with low-level infra, open-source engines (vLLM, SGLang, TRT-LLM), and PyTorch/C++/Python systems.
If you're passionate about pushing the limits of open-source AI infrastructure, Alan and I would love to connect.
👇 Apply here or drop me a message: https://lnkd.in/g5mtAUm8
tal saysbuild the fastest generative ai platform focusing on low-level llm infrastructure and open-source engines
ai-ml
series-b
pytorchc++pythonvllmsglang
comments 0 anon