Engineer II - AI Platform

Role Description

We’re looking for an AI Platform Engineer II to help build the secure, scalable foundations that power enterprise AI at ALSAC. In this role, you’ll design and develop core platform components—ranging from backend services and cloud infrastructure to the LLM systems that support our retrieval‑augmented generation (RAG) capabilities. You’ll work hands‑on with vectorization platforms, embeddings pipelines, APIs, and automation patterns that keep our AI environment reliable, compliant, and operationally ready.

As an Engineer II, you’ll independently own end‑to‑end delivery of moderate features and short projects, collaborate with senior engineers and cross‑functional teams, and mentor Engineer I‑level peers. Whether optimizing our LLM gateway architecture, improving observability across the platform, or contributing to scalable infrastructure‑as‑code, you’ll help shape the AI capabilities that drive innovation and directly support the mission of St. Jude.

Qualifications

• Bachelor’s in Computer Science, Software Engineering, Infrastructure Engineering, Cloud Engineering, or related field (or equivalent experience).
• 5–7+ years of experience in software development, infrastructure engineering, or cloud engineering, with demonstrated proficiency in either AI infrastructure or AI application development.
• Experience building backend applications and APIs (REST/GraphQL/gRPC) or developing user-facing AI applications.
• Familiarity with GenAI frameworks (LangChain, LlamaIndex, Semantic Kernel, etc.) or cloud-native development (AWS, Azure, GCP).
• Proficiency in at least one modern programming language (Python, Java, TypeScript, etc.).
• Experience with CI/CD pipelines and containerization (Docker, Kubernetes) is preferred.
• Strong problem-solving and collaboration skills.
• Excellent written and verbal communication skills.

Requirements

• Contribute to the development and maintenance of LLM gateways, retrieval-augmented generation platforms, or AI-powered applications.
• Design, develop, and maintain AI infrastructure or applications, ensuring secure, scalable, and enterprise-ready solutions.
• Participate in the integration of AI solutions with enterprise systems and data sources.
• Independently develop APIs and automation scripts for data integration and platform scalability.
• Support the implementation of security, compliance, and governance controls for AI systems.
• Assist with logging, monitoring, and reporting for auditability and usage insights.
• Develop and deploy AI applications using CI/CD pipelines and containerized environments (Docker, Kubernetes).
• Apply DevOps practices such as dependency management, vulnerability scanning, and role-based access as appropriate to project scope.
• Work with business/product stakeholders to translate requirements into AI features or applications.
• Collaborate with senior engineers and platform teams to adopt new capabilities and provide feedback.
• Participate in agile development processes (Scrum) to deliver projects efficiently.
• Mentor or review work from Analyst and Engineer I-level team members.
• Expand expertise in either AI infrastructure or application development, with opportunities to learn from senior engineers and cross-functional teams.
• Share knowledge and support peer learning within the team.

Benefits

• Core Medical Coverage: (low cost low deductible Medical, Dental, and Vision Insurance plans)
• 401K Retirement Plan with 7% Employer Contribution
• Exceptional Paid Time Off
• Maternity / Paternity Leave
• Infertility Treatment Program
• Adoption Assistance
• Education Assistance
• Enterprise Learning and Development
• And more