Elevate AI innovations as a Machine Learning Engineer focused on enhancing model optimization algorithms in remote workspace. Collaborate with product teams to streamline LLM training and deployment pipelines effectively.In this role, you will work as a key contributor on a dynamic team, developing cutting-edge deep learning software for various applications. Your main focus will be on improving inference performance through model compression techniques, collaborating closely with research teams to bring their ideas into robust production-ready systems. Expect to profile and enhance end-to-end LLM performance for optimal efficiency.Key Responsibilities:• Design and develop optimization algorithms for deep learning• Implement model compression pipelines using quantization techniques• Maintain speculative decoding frameworks for improved inference• Collaborate with research scientists on system development• Optimize LLM memory usage and latency for efficiencyRequirements:• Strong foundation in machine learning and deep learning• Proficiency in PyTorch or NumPy for model development• Demonstrated ability in Python for machine learning solutions• Familiarity with mathematical software and linear algebra• Degree in computer science or related field; PhD preferredBring your expertise to enhance model optimization and contribute to pioneering open-source AI developments.#J-18808-Ljbffr
Machine Learning Engineer Specializing In Model Optimization Algorithms
RED HAT, INC.
toronto, toronto
Published 27 days ago
Report job