As an ML Infrastructure Engineer at Hippocratic AI, your primary responsibilities will include building and maintaining infrastructure for deploying and managing Large Language Models (LLMs) at scale, implementing automated processes using tools like Kubernetes and Terraform, and optimizing resource usage across multiple cloud platforms. You'll also contribute to developing an orchestration platform and collaborate closely with ML engineers and DevOps teams to ensure smooth operations.

Candidates for the ML Infrastructure Engineer role at Hippocratic AI should have 3-5 years of experience in infrastructure engineering, DevOps, or a related field. Proficiency with Kubernetes and Terraform, experience with enterprise GPUs, and a basic understanding of ML workflows are essential. A bachelor’s degree in Computer Science or a related field is preferred, but equivalent experience will also be considered.

The ML Infrastructure Engineer at Hippocratic AI plays a vital role in supporting our mission to improve healthcare outcomes globally by designing and maintaining a high-quality orchestration platform. You will enable the efficient deployment and management of our Large Language Models, which are pivotal in offering safe and innovative AI solutions in healthcare environments, making a direct impact on health accessibility.

In the ML Infrastructure Engineer position at Hippocratic AI, you'll primarily work with Kubernetes and Terraform for infrastructure orchestration, as well as various cloud platforms, including AWS, Azure, and Google Cloud. Familiarity with programming languages like Python and Bash for automation is also beneficial, allowing you to streamline processes effectively.

The ML Infrastructure Engineer role at Hippocratic AI provides abundant opportunities for professional development through collaboration with leading experts in AI and healthcare. You will have a chance to learn about emerging technologies, contribute ideas to improve systems, and play a key role in expanding our innovative healthcare solutions.

In your response, highlight specific projects where you've successfully utilized Kubernetes to manage and orchestrate applications, especially focusing on how you handled scaling issues and maintained high availability of services.

Discuss a particular scenario where you used Terraform for Infrastructure as Code, detailing your thought process for defining your configuration, monitoring deployments, and addressing any issues that arose.

Share an experience that illustrates your problem-solving skills in a multi-cloud setup, focusing on the strategies you implemented to maintain performance and optimize resource usage across different cloud platforms.

Provide examples of how you've conducted capacity planning in previous roles, including the methodologies you used to forecast needs and the tools involved to ensure the infrastructure was scalable and cost-effective.

Explain the various tools and metrics you use to monitor system performance, identify bottlenecks, and ensure that your models function optimally over time.

Discuss your proficiency with languages like Python or Bash, providing specific examples of how you’ve used these languages to automate workflows and improve operational efficiencies.

Illustrate this with examples of successful projects where you've worked with ML engineers, DevOps teams, or other departments to achieve common goals, emphasizing your communication style and teamwork approach.

Share your methods for staying current, such as following industry publications, attending conferences, or participating in online communities related to AI and infrastructure engineering.

Provide a detailed account of the situation, your analysis of the problem, the steps you took to resolve it, and any lessons learned that improved your approach in the future.

Discuss your time management strategies and prioritization techniques, using examples from your experience to show how you balance competing demands and ensure project milestones are met.