AI Engineer

HUB International•Chicago, IL

6d•$135,000 - $160,000•Hybrid

About The Position

HUB International is seeking an AI Engineer to join the RPA & Automation team within its centralized technology organization and AI & Automation organization. This hands-on role designs, builds, and ships production-grade AI applications that deliver measurable value across HUB’s business lines. The role builds on Claude as HUB’s primary model platform, creating reusable skills and plug-ins, composing them into governed AI applications, establishing retrieval over governed enterprise data, and owning the AI asset platform used to deliver these capabilities. The technology stack is expected to evolve toward agentic systems. The AI Engineer turns experimental AI prototypes into governed, tested, enterprise-ready applications and owns enterprise standards and governance for skills, plug-ins, and MCP wherever they are used across HUB. The team builds simple-to-moderate skills, plug-ins, and MCP connections directly. Deep engineering work, such as new backend development, infrastructure, or complex integration, is routed to Enterprise Engineering, which executes against the team’s standards; the resulting assets are then governed and published by this role. The position is based out of HUB’s Chicago office in a hybrid work arrangement. The expected salary range is $135,000 to $160,000, with the final amount affected by skills, experience, work location, business line, scope, and level.

Requirements

At least 5 years of software or automation engineering experience, including at least 2 years building and shipping LLM-backed applications to production.
Direct, recent, hands-on experience building and publishing Claude skills or plug-ins; broad LLM or framework experience without shipped skills and plug-ins is not sufficient.
Strong Python, REST API, and enterprise integration skills, with sound fundamentals in testing, version control, and monitoring.
Hands-on experience with foundational models, including system and prompt design, skill and tool building, and function and tool calling.
Experience with retrieval-augmented generation, embeddings, and vector stores, including chunking and reranking.
Experience evaluating and monitoring LLM systems, with an understanding of cost, latency, and reliability tradeoffs.
Experience delivering within a regulated enterprise where security, governance, and access control are part of normal practice.
Cloud experience with Azure or GCP / Vertex AI.
A bachelor’s degree in Computer Science, Information Systems, Engineering, or a related technical field, or equivalent practical experience.

Nice To Haves

Agent development and orchestration experience, such as LangGraph, CrewAI, or Claude Agent SDK.
Model Context Protocol (MCP) design and agent-to-agent patterns.
Knowledge of identity and access concepts, including RBAC, non-human or agent identity, and least privilege.
UiPath or Power Platform exposure.
Insurance or financial services industry experience.
Familiarity with Git, CI/CD pipelines, modern software engineering practices, and tools such as Jira or Azure DevOps.

Responsibilities

Build reusable AI skills, package them as plug-ins, and compose them into governed applications for HUB business lines.
Configure and tune foundational models, including Claude and Gemini, for HUB use cases through system and prompt design.
Build retrieval-augmented generation, embeddings, and multi-step workflows over governed enterprise data.
Productionize business-built AI prototypes into reliable, governed applications.
Own and govern the skill and plug-in marketplace and MCP catalog, including intake, publishing, versioning, and maintenance.
Set and enforce enterprise standards and governance for skills, plug-ins, and MCP wherever they are used across HUB and on any surface, including Claude Code and builds executed by other engineering teams.
Apply access control, least privilege, and audit requirements to AI assets in partnership with Security and Cloud teams on identity and credentials.
Build simple-to-moderate skills, plug-ins, and MCP connections directly; route complex builds requiring new infrastructure or deep integration to Enterprise Engineering, then govern and publish the results.
Establish evaluation harnesses, golden-set testing, guardrails, monitoring, and logging to make AI outputs consistent and reliable at enterprise scale.
Provide production support for released skills, plug-ins, and applications.
Partner with business stakeholders to turn early-stage prototypes into production-ready, governed capabilities.
Work with Enterprise Engineering and data teams to deliver reliably and route deep engineering builds appropriately.
Participate in Agile ceremonies and document skills, applications, and technical decisions for handoff, audit, and maintenance.

Benefits

Competitive base salary and performance-based bonus.
Comprehensive medical, dental, and vision coverage.
401(k) with company match.
Paid time off and company holidays.
Hybrid work arrangement based out of the Chicago office.
Professional development and certification reimbursement.
Health, dental, vision, life, and disability insurance.
Flexible spending account (FSA) and 401(k) accounts.
Vacation, sick, personal, floating holiday, and company holiday paid time off, subject to applicable eligibility.
Eligible annual bonuses, equity, and commissions may be available for some positions.
Structured training, licensing support, and ongoing development opportunities.
Paid parental leave and a wellbeing program.
Company-paid life and disability plans.
Community impact opportunities through HUB Gives.