About Payliance

Founded in 2007, Payliance is a trusted leader in payment processing — processing more than $63 billion annually, supporting 40,000+ merchant locations, and serving over 350 lending clients. We offer an all-in-one platform for real-time funding, payment processing, account verification, and recovery services, giving lenders the technology to operate efficiently and confidently.

What sets Payliance apart is our blend of modern technology, deep industry expertise, and a highly collaborative, people-first culture. Our Architectural Services team exists to multiply that advantage — and AI Enablement is one of its cornerstone services. Backed by Serent Capital, we're expanding our capabilities, accelerating innovation, and investing in the infrastructure and talent needed to put safe, governed AI in the hands of every employee.

About the Role

The AI Enablement Engineer is a new, architect-track role on Payliance's Architectural Services team, owning the platforms, guardrails, and workflows that make AI genuinely useful across the company — for engineers and non-engineers alike. This role blends AI platform engineering, agent and skill development, identity-aware security architecture, and hands-on adoption enablement with a deep commitment to governed, measurable rollout. You'll build and operate the systems that let business analysts and other non-technical employees create, submit, and use AI agents safely — without needing engineering involvement beyond a formal review gate.

In payments, dependability is the product. AI capabilities at Payliance are held to the same standard as the payment platform itself: reliable, predictable, and available when the business depends on them. This role treats AI infrastructure as production infrastructure — with SLOs, observability, graceful degradation, and disciplined change management — not as an experiment that's allowed to fail quietly.

This role is ideal for a seasoned engineer growing into architecture: fluent in modern LLM platforms (Amazon Bedrock, Anthropic Claude), able to design and ship agentic workflows end-to-end, and bringing both the reliability discipline to run AI as a dependable service and the security discipline to enforce least-privilege access, per-user permission scoping, and auditable governance in a PCI-regulated payments environment. You'll author reference architectures and design decisions that other teams build on, with a growth path toward broader architectural leadership.

What You'll Do

AI Platform Engineering

· Operate and evolve Payliance's AI inference platform on Amazon Bedrock, including model selection, routing logic, and version pinning across the Claude model family.

· Build and maintain internal AI services and integration layers (C#/.NET, Python) that connect Claude to enterprise systems and workflows.

· Design cost-aware inference strategies — prompt caching, model tiering, and intent-based routing — that balance capability against spend.

· Own the reliability of AI services with the same rigor applied to the payment platform: define SLOs, build observability (logging, tracing, alerting), plan capacity, and design for graceful degradation when models or upstream services falter.

· Establish disciplined change management for AI infrastructure — pinned model versions, staged rollouts, and regression testing — so behavior never drifts silently in production.

Agent & Skill Development

· Design, build, and maintain Claude agents, Skills, and MCP (Model Context Protocol) integrations that connect AI to internal data sources and tools.

· Develop reusable agent patterns — retrieval, tool use, structured output, multi-step workflows — that other teams can adopt without starting from scratch.

· Author and curate high-quality prompts, skill definitions, and agent instructions, with versioning and review discipline.

· Evaluate agent quality systematically: define eval criteria, test for regressions, and validate behavior before promotion to production.

Governed Self-Service & Marketplace

· Operate and extend the internal AI skill/agent marketplace: submission pipelines, staging and curation workflows, and publication gates.

· Enable non-technical employees — business analysts and beyond — to create and submit agents and Skills through low-friction workflows that don't require engineering tooling or source-control accounts.

· Serve as a formal review gate for submitted agents and Skills: assess security posture, data access, prompt quality, and fitness for purpose before publication.

· Manage distribution across surfaces — Claude Enterprise, Claude Code, and internal applications — with consistent configuration and rollout controls.

Identity, Security & Governance

· Design and enforce identity-aware access to AI capabilities: SSO/SCIM provisioning, group-based entitlements, and per-user permission propagation to downstream data sources.

· Ensure AI tools respect existing data permissions — users should never see data through an agent that they couldn't access directly.

· Author and review least-privilege IAM policies for AI infrastructure; avoid broad credential grants in favor of scoped, auditable access patterns.

· Establish and maintain AI governance controls appropriate to a PCI-regulated payments environment: data handling policies, audit trails, and model usage boundaries.

Observability, Usage & Cost Management

· Build and maintain AI usage analytics and reporting: adoption metrics, token consumption, and cost breakdowns by team and use case.

· Deliver operational visibility to executive stakeholders through automated reporting and dashboards.

· Monitor for misuse, anomalous usage patterns, and quality degradation across deployed agents and Skills.

· Continuously optimize the cost/performance profile of AI workloads as models, pricing, and usage patterns evolve.

Adoption & Cross-Functional Partnership

· Partner with business teams to identify high-value AI use cases and translate them into working agents, Skills, and workflows.

· Train and coach non-technical builders on effective prompt design, agent construction, and responsible AI use.

· Author reference architectures, design decisions, and integration patterns that other engineering teams adopt — contributing to Architectural Services' broader practice.

· Collaborate with platform engineering and security teams on architecture decisions, integration patterns, and compliance requirements.

· Champion pragmatic AI adoption: cut through hype, set realistic expectations, and demonstrate measurable value.

Compensation & Benefits

· Competitive Base Salary based on experience.

· Performance-based annual bonus.

· Medical, Dental, and Vision insurance.

· 401(k) with company match.

· Generous PTO plus paid company holidays.

· Company-paid life and long-term disability insurance.

· Paid parental leave.

Work Environment

Remote-first with collaboration across U.S. time zones. This role does not carry a formal on-call rotation — dependability is achieved through resilient design, observability, and automation rather than pager duty. Cross-functional availability for working sessions with both engineering and business stakeholders is expected. Occasional travel may be required for team on-sites or company events.

Equal Employment Opportunity

Payliance is an equal opportunity employer. We value diversity and strive to create an inclusive workplace for everyone. Discrimination or harassment of any kind — based on race, color, sex, religion, sexual orientation, gender identity, national origin, age, disability, genetic information, or pregnancy — is not tolerated. Reasonable accommodations are available throughout the application and employment process.

What You'll Bring

Required Qualifications

· 5+ years in software engineering, platform engineering, or DevOps, with 1+ years of hands-on experience building with large language models in production.

· Practical LLM platform depth: Amazon Bedrock (or equivalent), model APIs, prompt engineering, structured outputs, and agentic/tool-use patterns.

· Software engineering ability in C#/.NET or Python — can design, build, and debug production services, not just scripts.

· Reliability engineering discipline: experience defining SLOs, building observability, designing for failure and graceful degradation, and operating services that other teams depend on.

· AWS fluency: compute (Lambda, ECS Fargate), IAM, networking fundamentals, and infrastructure-as-code (CloudFormation or CDK).

· Identity and access architecture experience: SSO (Entra ID or similar), SCIM provisioning, OAuth flows, and least-privilege permission design.

· Security-first mindset with practical experience scoping data access and building auditable, governed systems.

· CI/CD and workflow automation experience (GitHub Actions or similar) for building submission, review, and publication pipelines.

· Exceptional communication skills — able to teach AI concepts to non-technical audiences and translate business needs into technical designs.

Preferred Qualifications

· Direct experience with Anthropic's enterprise ecosystem: Claude Enterprise administration, Claude Code, Skills, and MCP server development.

· Experience in fintech, payments, or high-transaction-volume regulated environments (PCI-DSS, SOC 2).

· Familiarity with data lake and analytics governance: Lake Formation, Redshift, Athena, and permission-scoped query access.

· Experience designing LLM evaluation frameworks and quality gates for AI-generated content or agent behavior.

· Exposure to Microsoft 365 ecosystem integration: Teams workflows, Power Automate, and Entra ID group management.

· Bachelor's degree in Computer Science, Engineering, or related field (or equivalent hands-on experience).

How Your Success Will Be Measured

· Platform Dependability: AI services meet defined SLOs and availability targets, with no silent behavioral drift, clear runbooks, and rapid issue resolution.

· AI Adoption: Growth in active users, published agents/Skills, and business teams self-serving on the internal marketplace.

· Time-to-Value: Reduction in the time from idea to published, governed agent or Skill — especially for non-technical contributors.

· Governance Integrity: Zero incidents of AI-mediated data access exceeding a user's existing permissions.

· Review Quality: Submissions reviewed promptly with clear, actionable feedback and consistent standards.

· Cost Efficiency: AI spend per unit of value delivered, improved through routing, caching, and model tiering.

· Operational Visibility: Executive stakeholders have timely, accurate insight into AI usage, cost, and impact.

· Team Impact: Measurable lift in AI fluency across the organization through training, coaching, and reusable patterns.