LLM Inference Engineer (Mid, Sr, Staff)

The LLM Inference Engineer will own and optimize the serving infrastructure for healthcare AI, ensuring sub-100ms responses and reliable performance for millions of patient conversations. This role involves designing distributed serving architectures, implementing advanced quantization and speculative decoding techniques, and continuously benchmarking system performance. The engineer will drive lasting impact by improving latency, throughput, and cost efficiency while contributing to the core infrastructure's competitive advantage.