Staff Software Engineer - AI Platform

MeridianLink is a company focused on delivering AI-powered features consistently and at scale. This role is responsible for defining and building the shared AI platform that product and engineering teams use, requiring strong technical leadership and architecture skills across multiple teams.

Responsibilities:

• Makes critical architecture and design decisions that span multiple teams or an entire product area
• Evaluates technology choices with a clear view of trade-offs at scale, not just for the immediate problem
• Drives technical standards and patterns that other engineers can follow without being supervised
• Identifies systemic problems before they become incidents
• Provides day-to-day technical direction for one or more scrum teams without holding a management title
• Steps into ambiguous, high-stakes technical problems across teams and drives them to resolution — without being asked
• Holds a high bar in code and design review across team boundaries
• Designs shared AI platform services — including model integration layers, prompt management, retrieval-augmented generation infrastructure, embedding pipelines, and vector store management — that product teams can build on without re-solving the same problems
• Defines the reference architecture for how AI capabilities are consumed across products, including interface contracts, versioning, and deprecation strategies
• Evaluates and selects AI infrastructure components (cloud-managed model services, orchestration frameworks, vector databases) based on reliability, cost, latency, and operational complexity at scale
• Designs evaluation and monitoring pipelines that give teams visibility into AI output quality, latency, cost, and degradation over time
• Establishes guardrail patterns and content safety standards appropriate for a regulated financial services environment
• Defines the platform’s approach to compliance-relevant concerns: data residency, PII handling in AI pipelines, audit logging for AI-driven decisions
• Works with product engineering teams to understand how they want to consume AI capabilities, then translates that into platform APIs and abstractions that are ergonomic and consistent
• Builds the documentation, reference implementations, and onboarding paths that make the platform easy to adopt without hand-holding
• Identifies where product teams are solving similar AI problems in isolation and consolidates that work into shared platform capabilities
• Partner with product engineering teams and architects to catalog current and near-term AI use cases, identify common patterns, and define the platform services that should be centralized
• Produce technical designs — RFCs, architecture decision records, system diagrams — for AI platform components at a level of detail that other engineers can implement and review against
• Evaluate third-party AI infrastructure options (model providers, vector databases, orchestration frameworks) and make build-vs-buy recommendations with clear rationale
• Lead development of core AI platform services: model serving and routing, retrieval infrastructure, prompt management, output evaluation, and usage observability
• Define and enforce integration standards — API contracts, error handling patterns, cost attribution — so that product teams building on the platform do so consistently
• Own the technical roadmap for the AI platform, prioritizing based on what unblocks the most product development and reduces the most duplicated effort
• Develop Senior engineers toward Staff-level scope; give them problems and opportunities that stretch them, not just guidance on their current work
• Partner with Engineering Managers and Product leadership to align technical decisions with delivery goals
• Own the design and maintenance of technical knowledge infrastructure — RFCs, ADRs, runbooks, onboarding paths — so teams can operate without needing to escalate

Requirements:

• 8+ years of professional software engineering experience, with demonstrated technical leadership across multiple teams or product areas
• Proven ability to make and defend architecture decisions at scale
• Active daily use of AI-assisted development tools
• Bachelor's degree in Computer Science, Software Engineering, or equivalent experience
• 3+ years of hands-on experience designing or building systems that integrate large language models or other ML models into production software
• Demonstrated experience building shared platform services or internal developer platforms, not just application-level features
• Proficiency with cloud-managed AI services (AWS Bedrock, Azure OpenAI, or equivalent) and the operational characteristics of running AI workloads in production
• Strong understanding of retrieval-augmented generation architectures, vector search, and embedding pipeline design
• Experience designing systems in regulated industries where data handling, audit trails, and compliance constraints shape technical decisions
• Experience in fintech, banking, or other regulated financial services environments
• Familiarity with AI evaluation frameworks and techniques for measuring output quality and detecting model degradation
• Experience with prompt management, versioning, and experimentation at scale
• Prior work on developer-facing platforms with a focus on adoption and internal developer experience