Principal AI Platform Engineer

Who you are

You have extensive experience building and maintaining AI platform infrastructure, particularly with Kubernetes and container security — you've designed systems that ensure secure and efficient operations in production environments. Your expertise in observability and monitoring frameworks is demonstrated through your work with real-time performance tools like OpenTelemetry and MLFlow, allowing you to ensure that AI workloads run smoothly and efficiently.

You are familiar with AI infrastructure components such as vector databases and prompt/versioning stores — your background includes working with AI IDEs that facilitate the development and deployment of machine learning models. You have a strong understanding of authentication and authorization frameworks, ensuring that security is integrated into every aspect of the AI platform.

Your collaborative spirit shines through as you work closely with product and engineering teams — you understand the importance of integrating AI infrastructure with existing agent frameworks and downstream applications to deliver seamless user experiences. You are adept at optimizing infrastructure for scalability, high availability, and cost efficiency, ensuring that the AI products you support can handle increasing demands.

Desirable

Familiarity with frameworks like vLLM and SGLang is a plus, as it enhances your ability to host LLM inference workloads effectively. Experience with CI/CD pipelines and automation for AI model deployment is also beneficial, as it aligns with your goal of streamlining operations and improving deployment efficiency.

What you'll do

As the Principal AI Platform Engineer, you will be responsible for designing, building, and maintaining the core infrastructure layer that supports generative AI products — this includes developing model gateways, prompt/versioning stores, and vector databases that are crucial for delivering AI-generated insights. You will implement secure access controls and authentication mechanisms that are integrated by default into the AI platform components, ensuring that security is a top priority.

You will develop and manage observability, monitoring, and logging solutions for GenAI workloads and infrastructure — your role will involve collaborating closely with product and engineering teams to integrate the AI infrastructure with agent frameworks and downstream applications, ensuring that the systems work harmoniously together.

Your focus will be on optimizing the infrastructure for scalability and high availability, as well as ensuring cost efficiency for production workloads — you will analyze performance metrics and make recommendations for improvements based on your findings. You will also play a key role in mentoring junior engineers and sharing your knowledge of best practices in AI infrastructure development.

What we offer

At PointClickCare, you will be part of a centralized team that specializes in generative AI capabilities — you will have the opportunity to work on high-impact AI products that are designed to transform workflows and enhance user experiences. We foster a collaborative environment where your contributions will directly influence the success of our AI initiatives.

We encourage you to apply even if your experience doesn't match every requirement — we value diverse perspectives and believe that a variety of experiences can lead to innovative solutions. Join us in our mission to deliver safe, scalable, and impactful AI products that make a difference in the healthcare industry.