ML Engineer, Inference and Serving

Firebird.ai is seeking a skilled Machine Learning Engineer to focus on the deployment and optimization of machine learning systems, particularly in model serving and inference performance. The role involves designing and optimizing large language model (LLM) inference systems for production, evaluating performance metrics such as latency and throughput, and implementing solutions using frameworks like vLLM and TensorRT-LLM. Candidates should have over three years of experience in ML engineering, specifically in model deployment and inference, and must have hands-on experience with at least two of the mentioned frameworks under real traffic conditions. A solid understanding of LLM inference internals is also required. The position is based in Yerevan and is a permanent role, suitable for individuals who enjoy collaborating with cross-functional teams to enhance AI services and improve operational excellence. The ideal candidate will stay updated on advancements in LLM serving and AI infrastructure technologies.