AI Solution Architect

Position Summary:

The AI Solution Architect plays a critical role in advancing JSSI’s AI First engineering strategy and execution from concept to production. Reporting to the Director of Engineering, this role helps shape and drive the architecture standards and execution for AI agents, spec-driven development (SDD), and enterprise automation, spanning Engineering, Product, Sales, Finance, Customer Service, and Operations.

This is a hands-on, high-ownership role: you will design, build, and deploy AI systems rapidly and own their outcomes, measured on impact rather than intent. Success demands as much from your ability to listen, communicate, and influence as from your technical depth. You will engage business stakeholders across the organization, translate their needs into scalable solutions, and guide others toward better outcomes.

Position Responsibilities:

AI First Architecture & Delivery

• Own the AI First architecture for JSSI's software delivery lifecycle, rolling out spec-driven delivery models and bringing AI agents into day-to-day engineering across teams, working toward a target of 100% of all code being generated by AI.
• Lead integration and adoption of AI tools, agents, agent skills, and services across specification, development, review, testing, documentation, and release, driving both technical connection and day-to-day uptake by engineering teams.
• Build and maintain AI frameworks enabling scalable fine-tuning and prompt engineering pipelines, inference, experiment tracking, observability, and model governance.
• Architect multi-agent systems (orchestration, reasoning, planning, autonomous task execution) on layered, distributed architectures (queues, caching, APIs, database schemas) operated by teams of coding agents.
• Translate Agile artifacts (epics, user stories, acceptance criteria) and product inputs into structured, agent-ready specifications that coding agents implement.
• Set technical standards for API design and interoperability, along with the guardrails, evaluation frameworks, and agent behavior boundaries that ensure responsible, predictable AI deployment.
• Design, build, and evaluate MCP servers that expose JSSI enterprise systems as model-ready tools, and define criteria for assessing third-party MCP integrations for security, reliability, and production readiness.

Enterprise Automation

• Design, build, and maintain agent-based automation that coordinates LLMs, tools, APIs, and enterprise data (Salesforce, email, BI tools, data lakes) into cohesive, production-grade workflows.
• Establish patterns for agent reliability, observability, fallback behavior, and lifecycle management in production.
• Develop enterprise-grade internal and external applications and services (dashboards, microservices) that operationalize and extend automation initiatives.
• Create and refine AI prompts, then monitor, troubleshoot, and optimize automations for accuracy, performance, and business value.
• Build trusted relationships with cross-functional stakeholders, develop deep business insights and understanding, and translate them into a prioritized pipeline of high-impact, value-added opportunities.
• Support infrastructure teams in building CI/CD pipeline automation, security scanning, and policy-enforcement agents, providing reusable patterns and ongoing architectural support so they can extend and maintain it.

Engineering Leadership & Standards

• Operate on the front line of AI delivery, building enterprise-class products firsthand and treating rapid experimentation as an operational-excellence discipline, deploying and learning in tight cycles toward a future state of deploying to production many times per day.
• Partner with engineering teams and leadership to shape engineering-practice standards, governance, and metrics that improve speed, quality, consistency, and business impact.
• In a fast-moving AI landscape, partner with Engineering, Product, and Executive leadership to refine processes, define metrics that quantify impact, scale proven workflows into repeatable delivery models, and manage dependencies and technical risk across concurrent efforts.
• Guide and mentor AI Engineers and AI Verification Architects through technical leadership and influence rather than direct people management, fostering a calm, supportive, and solution-oriented culture.
• Recognize the growing importance of citizen developers to the business, and provide the guidance, partnership, best practices, and insight that help their teams succeed.
• Ensure responsible AI practices: fairness, explainability, model monitoring, ethics, and regulatory alignment.

Required Qualifications:

Core Experience

• 6-10 years of overall software engineering experience, including 3-5 years in a Solution Architect, Staff/Principal Engineer, or equivalent senior technical role with ownership of system design for production SaaS platforms.
• Demonstrated experience designing and implementing AI First, spec-driven (SDD) workflows across the software delivery lifecycle
• Production-level, cloud-native development in the Microsoft stack (C#/.NET, React/TypeScript, RESTful Web APIs, SQL Server / Azure SQL Managed Instances) and distributed-systems patterns such as queues, caching, and scalable APIs.
• Experience building, deploying, and maintaining production services through CI/CD and rapid, iterative release cycles, not just prototypes.
• Proven ability to mentor engineers and guide multiple teams through influence rather than direct people management.
• Excellent written and verbal communication skills; able to translate technical concepts for non-technical audiences.

AI & Claude Ecosystem Proficiency (Claude Strongly Preferred)

• Hands-on experience with AI coding agents and agentic workflows (Claude Code strongly preferred; also GitHub Copilot, Codex, or equivalent), including CLI integration and multi-agent development pipelines.
• Strong prompt engineering skills, including structured outputs and retrieval-augmented prompting.
• Production expertise with LLM APIs (Claude API preferred): tool use, computer use, vision, document processing, streaming, and rate-limit management.
• Hands-on experience with multi-agent design patterns (planning, orchestration, observability) and MCP server implementation against enterprise data sources.
• Software engineering best practices (version control, testing, deployment pipelines), evaluation frameworks that measure AI quality, cost, and latency, and responsible-AI design aligned with Anthropic's principles.

Highly Desired Qualifications

• Experience rolling out and scaling AI workflows across teams, including agent observability and debugging in production.
• Experience with Azure cloud infrastructure and integrations with enterprise systems such as Dynamics 365 F&O and Salesforce or equivalent CRM.
• Bachelor’s degree in Computer Science, Information Systems, or equivalent professional experience.