Staff Software Engineer ( AI )

Staff Software Engineer ( AI ) As a senior individual contributor and one of the highest-ranking technical voices in our engineering organization, the Staff Software Engineer (Professional 5) plays a pivotal role in shaping our AI platform strategy. This role, part of the Platform Services team, is dedicated to designing and building foundational infrastructure to power MeridianLink’s expanding suite of customer-facing AI capabilities across our credit union software product lines. Rather than focusing solely on implementation, the Staff Engineer acts at the intersection of architecture, strategy, and hands-on technical delivery. You’ll own the technical direction for AI platform systems, establish standards and patterns, and lay the architectural groundwork to enable reliable, scalable, and responsible AI development. This engineer will report directly to the Director of Platform Services and exert significant cross-functional influence across multiple engineering teams. As our AI platform matures—from third-party LLM integrations toward custom model development—your responsibilities will evolve, giving you increasing ownership over our model infrastructure, evaluation harnesses, and data pipelines needed to support production-grade AI in a regulated financial environment. This fully remote position works within a sub-team in Platform Services, responsible for building and scaling MeridianLink’s first generation of customer-facing AI capabilities. The team closely partners with application engineering, cloud infrastructure, and applied AI, creating technological foundations vital for delivering intelligent features to our credit union clients. Key Competencies - Technical Mastery & Architecture: Define multi-team strategy, address architectural bottlenecks, and evaluate build vs. buy decisions across the platform. Architect scalable AI systems with security, compliance, and developer experience at the core. - Organizational Influence: Lead cross-team architecture reviews, drive collaborative alignment, establish engineering best practices, and set the bar for design reviews and production readiness. - AI & GenAI Platform Expertise: Leverage hands-on knowledge of LLM/GenAI application patterns (e.g., prompt management, RAG pipelines, evaluation harnesses) and design for safety, auditability, and compliance in financial services AI. - Mentorship: Mentor and sponsor engineers at L3–L4 levels, facilitate knowledge sharing, and drive tech debt and best practice initiatives for engineering excellence. - Stakeholder Engagement: Author clear, auditable architectural documentation; translate technical concepts for business partners; and partner with Product on business requirements and roadmaps. Expected Duties Architectural Leadership - Own the reference architecture for the AI platform, encompassing API abstractions, prompt and version management, RAG infrastructure, vector retrieval, evaluation harnesses, and model serving. - Lead build-vs-buy evaluations for AI components, including due diligence and integration planning. - Design foundational data pipelines and infrastructure to support reliable, scalable AI services. - Define and document API contracts, standards, and platform interfaces across engineering. Hands-On Delivery - Contribute to backend development in Python and RESTful API design, including integrations with leading AI providers. - Participate in full-stack delivery when needed, using React/TypeScript/Vite to deliver AI features. - Build and maintain tooling, SDKs, and platform APIs to enable safe, scalable AI adoption by product teams. - Drive improvements to AI-assisted development workflows with tools like GitHub Copilot and Claude. AI Platform Development - Implement integrations with LLMs: context management, prompt templating, response validation, and robust fallback strategies. - Build and maintain evaluation frameworks for reproducible model testing. - Establish observability and per ... (truncated, view full listing at source)