Applied AI Data Platform Engineer (Full-Stack)

NorthStar Memorial ll, a close partner of Karmel Capital, is seeking an Applied AI Data Platform Engineer (Full-Stack) to design, build, and operate internal platforms and tools that power team workflows. This role sits at the intersection of software engineering, data engineering, and applied AI, with responsibility for turning loosely defined business needs into reliable, production-grade

systems. You will work across the full stack, building user interfaces, backend services, data pipelines, and AI-driven workflows, while helping evolve successful internal tools into durable, standardized platforms that others can depend on. This is an ideal role for someone who enjoys combining product thinking, technical

breadth, and operational ownership to solve real business problems.

What You’ll Do:

Internal Web Apps & Tooling

• Build internal dashboards, admin tools, and workflow-oriented applications that streamline operations
• Translate ambiguous business needs into shippable features spanning UI, APIs, and data models
• Iterate quickly based on real-world usage and feedback
• Improve usability through clearer workflows, better information design, and reduced friction
• Help turn successful one-off tools into durable internal products with stronger documentation, UX consistency, and long-term supportability

Data Platform & Integrations

• Integrate third-party systems and APIs, normalizing disparate inputs into clean internal formats
• Build ingestion pipelines and jobs across the full lifecycle: fetch, validate, transform, store, and serve
• Maintain data quality over time through deduplication, merges, schema evolution, and pragmatic quality checks
• Improve retrieval and system performance where it materially matters through indexing, caching, and query optimization
• Productize critical pipelines so they are observable, repeatable, and dependable for internal stakeholders

AI / LLM Workflows

• Build pipelines that use LLMs to transform unstructured inputs into structured,
• usable outputs, including summarization, classification, extraction, routing, tagging, and enrichment
• Implement practical guardrails to improve consistency and reliability, including versioning, fallbacks, cost controls, and lightweight evaluation/QA
• Design outputs to be traceable, reviewable, and easy to use within internal tools
• Evaluate AI vendors and model APIs based on capability, quality, latency, cost, integration fit, and edge case behavior
• Productionize AI capabilities once they demonstrate clear business value.

Backend Services & Systems

• Build and maintain backend services that support internal applications, integrations, and automations
• Own API design patterns, background processing systems, and shared technical foundations used across multiple tools
• Write maintainable, well-structured code with pragmatic testing, logging, debugging, and support practices
• Establish stable interfaces and operational standards so systems can scale beyond a single maintainer

DevOps, Infrastructure & Operations

• Deploy and operate systems end-to-end across environments, CI/CD, monitoring, logging, performance, and production support
• Improve reliability over time through operational hardening and better engineering practices
• Automate repetitive setup, deployment, and maintenance work
• Document systems and workflows so that core operational knowledge is repeatable and not dependent on tribal knowledge

What We’re Looking For

• Strong full-stack engineering skills with experience building internal or customer-facing web applications
• Experience working with APIs, backend services, and data pipelines
• Hands-on familiarity with applied AI/LLM workflows in production or near-production settings
• Ability to take loosely defined problems and turn them into practical, reliable systems
• Strong product instincts and a bias toward usability, maintainability, and operational excellence
• Comfort working across multiple domains, from front-end UX to backend architecture to data workflows and infrastructure
• Strong judgment on when to prototype quickly and when to harden systems for broader adoption
• Clear communicator who documents decisions and builds tools that teams can actually use

Nice to Have

• Experience building internal platforms, workflow tools, or operational systems
• Familiarity with vector databases, retrieval systems, or AI orchestration frameworks
• Experience evaluating or integrating third-party AI/LLM vendors
• Exposure to observability, CI/CD, infrastructure automation, and production operations
• Experience evolving prototypes into stable internal products

Why This Role Matters

This role is central to improving internal leverage. You will help the team at NorthStar Memorial Group llc move faster by building tools and systems that reduce friction, improve reliability, and unlock the practical value of data and AI across workflows. Your work will directly shape how new capabilities are conceived, built, and scaled.