AI Application Engineer

PartsSource Inc. is the leading technology and software platform for managing mission-critical healthcare equipment. They are seeking an AI Application Engineer to design, develop, and deploy applications powered by Large Language Models (LLMs), focusing on creating robust, scalable, and data-driven solutions.

Responsibilities:

• Design and implement production-grade applications that integrate LLMs to deliver intelligent, user-centric solutions
• Develop and orchestrate complex LLM workflows to enable agentic systems capable of autonomous decision-making and task execution
• Apply software engineering best practices, including modular design, testing, and CI/CD, to ensure high-quality, maintainable codebases
• Utilize a data-driven approach to develop, evaluate, and optimize LLM interactions, incorporating metrics, experimentation, and iterative research
• Collaborate with cross-functional teams, including data scientists, product managers, and UX designers, to align AI solutions with business objectives
• Stay up-to-date with emerging AI technologies, tools, and frameworks to drive innovation in application development
• Deploy and manage applications on cloud platforms, ensuring scalability, reliability, and security

Requirements:

• Bachelor's degree in Computer Science, Engineering, or a related field (or equivalent experience)
• Proven experience in software engineering, including designing, developing, and deploying production-grade applications
• Strong understanding of data-driven development, including experimentation, evaluation, and optimization of AI models and interactions
• Knowledge of agentic systems and their applications in automating complex tasks
• Excellent problem-solving skills and ability to work in a fast-paced, collaborative environment
• Hands-on expertise with Genkit for orchestrating LLM workflows and building agentic systems
• Familiarity with Firebase for rapid development, authentication, and real-time data management
• Strong proficiency in TypeScript for building robust, type-safe applications
• Experience with Google Cloud Platform (GCP), including Vertex AI and Gemini, for deploying and managing AI workloads
• Experience with other cloud platforms (e.g., AWS, Azure) and their AI/ML services
• Familiarity with additional AI frameworks or libraries for building and evaluating LLM-based applications
• Background in researching and experimenting with LLMs to improve performance and user experience
• Understanding of DevOps practices, including containerization (e.g., Docker) and orchestration (e.g., Kubernetes)