? Do you thrive on taking experimental code and turning it into robust, scalable, and high-performance production systems? At Maersk.... Architect Scalable Inference: Build and maintain high-throughput, low-latency AI/ML model serving systems. Optimize...
-grade LLM solutions, run experiments, and work directly with the Lead Architect - AI What You'll Build: LLM-powered... (Transformers, PEFT, Datasets), LangChain, and LlamaIndex Performance monitoring - Define metrics, track model drift, and maintain...
of innovative technologies, including ultra-fast read channels, high-performance processors, leading edge transceivers, highly... experts to develop compiler and runtime infrastructure to achieve the targeted features and performance benchmarks...