Staff Software Engineer - AI Products

Open 54d

Position Summary

This role is the technical lead for MeridianLink’s customer-facing AI product engineering. The Staff Software Engineer - AI Products sits on our AI Products team and owns the architecture and delivery of intelligent features going directly into the hands of credit union clients. This is the first generation of AI-native products at MeridianLink, and this engineer sets the technical bar for how those products are built: from feature architecture and LLM integration patterns to evaluation quality and production reliability. They partner closely with the AI Platform team to leverage foundational infrastructure and with Product Management to translate business intent into well-designed AI features.

Key Competencies

Staff engineers operate across multiple teams or an entire product line. They set technical direction, make architecture and technology decisions that others build against, and raise the engineering floor across the teams they touch. Staff engineers at MeridianLink are active, daily users of AI-assisted development tools -- and go further by building the workflows, tooling, and patterns that make those tools more effective for the teams around them.

Technical Leadership & Architecture

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
Reasons fluently across the fundamentals of distributed systems: how systems handle load, how they store large datasets, and how they stay correct under failure
Treats every architecture decision as a trade-off between speed, cost, and correctness, and makes that trade-off explicit when guiding teams; sizes systems with back-of-the-envelope estimation and decides microservices versus monolith on evidence rather than default

Cross-Team Execution

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

AI Feature Architecture & Quality

Designs customer-facing AI features with reliability, correctness, and user trust as primary constraints

Defines evaluation and testing standards for LLM-integrated systems, including prompt regression testing, output quality metrics, and human evaluation criteria

Architects AI features to degrade gracefully when model outputs are low-confidence or unexpected, maintaining a reliable user experience in production

Balances AI capability decisions against compliance constraints relevant to regulated financial services

AI Product Engineering

Applies deep practical knowledge of LLM application patterns: prompt engineering, context management, RAG pipelines, agentic workflows, and provider integration

Makes informed decisions about AI capability design: when to use retrieval vs. fine-tuning, when to call the model vs. use deterministic logic, and how to structure multi-step AI workflows

Works fluently across the full stack of AI product delivery -- from backend LLM integration to the frontend surfaces users see

Interfaces with the AI Platform team to consume shared infrastructure and feeds real-world product requirements back into platform prioritization

Product Partnership & Stakeholder Influence

Partners with Product Management to translate business requirements and user needs into concrete AI feature designs, contributing technical feasibility while incorporating market and customer context

Communicates architectural tradeoffs and product constraints clearly to non-technical stakeholders, including product leadership

Produces RFCs and ADRs that capture durable decisions for AI features and serve as shared reference for future product work

Shapes the roadmap of AI feature investment by surfacing technical risk, capacity constraints, and platform dependencies early

Expected Duties

AI Feature Architecture & Technical Direction

Own the reference architecture for customer-facing AI features, including LLM integration patterns, prompt management, context strategies, retrieval design, and response validation

Lead architecture reviews for new AI features, setting the technical standard for how AI capabilities are designed and evaluated before implementation begins

Drive build-vs-integrate decisions for AI feature components, evaluating third-party tooling, platform capabilities, and custom development tradeoffs

Define and document API contracts, data flows, and system integration patterns for AI features that span product surfaces

AI Product Delivery

Contribute directly to AI feature implementation across the full stack: backend LLM integrations in Python, RESTful service design, and frontend surfaces in React and TypeScript

Build and maintain evaluation harnesses and testing frameworks that give the team confidence in AI feature quality before and after release

Establish observability patterns for AI features, including latency tracking, error rates, model quality signals, and user feedback loops

Validate and continuously improve AI-assisted development workflows, using tools like GitHub Copilot and Claude to accelerate team delivery

Platform Collaboration & Compliance Awareness

Work closely with the AI Platform team to leverage shared infrastructure -- vector search, model gateways, prompt management services -- and surface requirements that should be addressed at the platform layer

Apply secure-by-default design practices, including least-privilege access controls, audit logging, and encryption appropriate for systems handling financial member data

Maintain working familiarity with data privacy and compliance expectations relevant to regulated financial services, enabling productive collaboration with compliance stakeholders

Collaborate proactively with the Security team during feature design to ensure AI capabilities meet security requirements before implementation begins

Collaboration & Growing Others

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

Qualifications: Knowledge, Skills, and Abilities

Required

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

Demonstrated experience building and shipping customer-facing AI or LLM-integrated features in production environments

Strong proficiency in Python for backend and service development, including RESTful API design with frameworks such as FastAPI or Django

Hands-on experience with LLM integration patterns, including prompt engineering, context management, RAG pipelines, and provider APIs (e.g., OpenAI, Anthropic)

Experience building and maintaining evaluation frameworks for LLM-based systems, including output quality testing and regression detection

Solid working knowledge of modern frontend development (React, TypeScript) sufficient to contribute to and review AI feature surfaces

Experience deploying and operating applications on AWS, including IAM, managed services, and cloud-native architecture

Preferred

Prior experience building software in a financial services, fintech, or other regulated technology environment

Familiarity with AI compliance and governance considerations applicable to financial institutions (e.g., model risk management, fair lending, NCUA guidance)

Experience with vector databases and semantic search infrastructure (e.g., pgvector, Pinecone, OpenSearch)

Working knowledge of AI evaluation tooling or experiment tracking frameworks (e.g., LangSmith, MLflow, Weights & Biases)

Exposure to agentic workflow patterns, multi-step AI orchestration, or tool-use implementations

What Success Looks Like

A successful hire at this level establishes themselves quickly as the architectural voice for AI feature quality and delivery on the team. In the first few months, they are setting technical direction on active AI features, raising the evaluation bar so the team ships AI capabilities with confidence, and building a productive working relationship with the AI Platform team. Over time, their impact is measured in the quality and reliability of AI features reaching clients, the technical growth of the engineers around them, and how well the team’s AI architecture holds up as the product portfolio expands.

Show

What this application asks

ashby

Name, Email, Resume

Are you eighteen years of age or older? yes / no
May MeridianLink contact your CURRENT or MOST RECENT employer? yes / no
May MeridianLink Contact your PAST employers? yes / no
Have you ever been fired or asked to resign to avoid being fired from a job? yes / no
Can you perform the essential functions of this job with or without reasonable accomodation? yes / no
Will you now or in the future require sponsorship (i.e. H-1B visa ect.) to legally work in the United States? yes / no
Location
I understand that as permitted by law, MeridianLink will conduct an investigative consumer report. I understand the scope of this consumer report may include verification of my references, employment history, credit and indebtedness, criminal conviction history, educational and training background and other matters related to my suitability for employment. Upon timely written request to the personnel department of MeridianLink, the nature and scope of the report will be disclosed to me. If I am offered employment with MeridianLink, I understand that the offer will be conditioned on passing a pre-employment drug screen, timely submitting valid documentation that confirms my identity and authorization to work in the United States, and reading and agreeing to comply with the MeridianLink policies as stated in its Employee Handbook. I certify that the answers given by me in this employment application are true, correct and complete. I agree that the company shall not be liable, in any respect, if my employment is terminated because of misstatements or pertinent omissions made by me in this application. Moreover, I understand that all offers of employment are contingent upon passing the company's prescribed credit check and background screen. A copy of this form may be used as the original. The use of results from this form and/or tests will be used for prudent employment decisions. It is agreed and understood that completion of this application does not mean a job opening exists and in no way obligates the company to employ me. In the event of employment, I will comply with all company rules and regulations as established from time to time. I am willing to work all assigned overtime or other special work assignments as requested by the company. I also understand that MeridianLink, Inc. retains the right to amend, modify, add or delete any or all policies or procedures at its sole and absolute discretion. I understand that nothing contained herein is intended to create a contract between the company and me for either employment or the provision of any compensation or benefits. I hereby understand and acknowledge that any employment relationship with this Company is of an “At-Will” nature, which means that the Employee may resign at any time and the Employer may discharge Employee at any time, with or without notice, with or without cause. It is further understood that this ‘At-Will’ employment relationship may not be changed by any written document or by verbal agreement unless such change is specifically acknowledged in writing by an authorized Executive of this Company. During my employment with MeridianLink, Inc. and after my employment ends, I agree not to disclose any confidential or proprietary information regarding operating and trade secrets. CERTIFICATE OF APPLICANT: I certify that all statements made in this application and attachments are true, and I agree and understand that misstatements or omissions of any material fact may be cause for disqualification or dismissal from employment with MeridianLink choose one
Please let us know where you heard about this job opening? choose one
If above question is "Other" please add the source below. written answer · optional