Description
Mirendil is hiring an Inference Engineer to own the inference systems powering frontier AI models in production and research. The role covers high-throughput, low-latency serving infrastructure, GPU and accelerator optimization, distributed inference frameworks, inference-time techniques such as speculative decoding and quantization, observability, and collaboration with model and post-training teams. The position offers a base salary of $300,000–$400,000 USD and a meaningful equity grant, along with competitive benefits.
