Responsibilities

📍Collaborate with cross-functional teams to deploy and maintain AI models in production environments, ensuring scalability, reliability, efficiency, and robustness 📍Orchestrate model serving to accommodate our unique infrastructure in a scalable manner 📍Maintain backend planning and optimize GPU capacity continuously 📍Build tools for end-to-end ML model deployment and lifecycle management 📍Build tools to monitor model performance 📍Recommend options for end-to-end Ops pipelines that are needed to drive various business plans 📍Stay up-to-date with the latest advancements in AI technologies and research, and apply them to enhance performance and capabilities

Qualifications

📍Bachelor's or Master's degree in Computer Science, AI/ML, or a related field 📍2+ years of professional ML deployment experience on scale, preferably MLOps for LLMs and/or diffusion models 📍2+ years of experience with cloud platforms (e.g., AWS, Azure, OCI, Google Cloud) and experience with deploying AI models in cloud-based environments 📍Proficiency in containerization technologies as Docker, inference servers as Triton and container orchestration platforms as Kubernetes 📍Proven experience in working with and scaling GPUs 📍Experience partnering with back-end & front-end eng to tie AI/ML infrastructure to a scaled front-end experience 📍Strong knowledge of Python, with experience in popular machine learning libraries (e.g., TensorFlow, PyTorch, Spark) 📍Solid understanding of machine learning concepts and algorithms. 📍Extensive Linux troubleshooting experience 📍Excellent problem-solving and analytical thinking skills, with a strong attention to detail 📍Effective communication and teamwork abilities, with the capacity to work in a fast-paced, collaborative environment