AI Engineer

Chicago, Illinois

Direct Hire

Salary Range : $120,000 - $160,000

Benefits : Full benefits start on day 1 Company provides an employer match to employee 401(K) contributions by matching 75% of employee contributions on up to 6% of eligible earnings, FTO - flexible time off - no limit Industry-leading benefits plans

AI Engineer


POSITION SUMMARY


The AI Engineer is a hands-on builder at the core of our organization's AI First engineering transformation, designing, shipping, and operating production-grade AI systems from prototype to production. Reporting to the Director of Engineering, you will work alongside the AI Solution Architect (who sets architecture standards and direction) and the AI Verification Architect (who builds the testing and verification frameworks your work is validated against), partnering closely with an AI First Product team to drive the evolution of our SaaS platforms.


This is a distinct role that supersedes the traditional Senior Developer position. In an AI First Agentic Operating model, "senior developer" is no longer a job a person holds: it is a capability the AI Engineer directs, exercised by coding agents under their guidance. The AI Engineer orchestrates that agentic development capability rather than performing hands-on coding as the primary activity, owning outcomes across building, shipping, and operating AI systems. It is designed for accomplished software engineers ready to make that shift, from writing the code themselves to directing the agents that write it.


You will turn product specifications and Agile artifacts into working AI agents, LLM-powered features, and automation; integrate them with enterprise systems; and own their reliability, accuracy, and business impact in production. You will use Claude Code as your primary development tool, working in tight build-measure-learn cycles. Success is measured by what you ship and the outcomes it produces, not by activity. Strong written and verbal communication matters as much as technical depth: you will collaborate daily with product, business stakeholders, and your engineering peers to translate real needs into reliable solutions.


POSITION RESPONSIBILITIES:


AI First Engineering & Delivery

• Drive continuous refinement of the AI agentic pipeline and its iterative development loop, informing architectural direction in partnership with the AI Solution Architect. Apply context engineering, enforce human-in-the-loop governance, and hold final accountability for all software delivered under your direction.
• Direct the design, build, and delivery of production-grade AI features and agents across the organization's SaaS platforms, working within the architecture standards and spec-driven delivery models set by the AI Solution Architect.
• Implement and integrate AI tools, agents, agent skills, and services across the delivery lifecycle: specification, development, review, testing, documentation, and release.
• Build multi-agent workflows (orchestration, reasoning, planning, autonomous task execution) on distributed patterns such as queues, caching, and scalable APIs, and operate them with other coding agents.
• Translate Agile artifacts and product inputs into structured, agent-ready specifications, implement them through coding agents, and build and consume MCP servers that expose enterprise systems as model-ready tools, following the criteria defined by the AI Solution Architect.
• Use Claude Code as your primary enablement tool to develop, review, test, and document software in tight, iterative cycles, adopting spec-driven delivery models and bringing AI agents into day-to-day engineering, with a stated goal of 100% AI-generated code.
• Serve as the primary steward of the context store, the coding standards, patterns, domain knowledge, and project memory that ground every agent session, capturing each lesson and production insight back into it to continuously improve the pipeline.
• Bridge spec-driven and test-driven practices: derive tests directly from the spec's acceptance criteria before directing agent implementation, making the spec executable, structurally constraining agent output, and giving the AI Verification Architect a reliable contract to validate against.

Enterprise Automation

• Build, operate, and maintain agent-based automation that coordinates LLMs, tools, APIs, and enterprise data (across major ERP, CRM, and internal proprietary platforms) into cohesive, production-grade workflows, following the automation patterns and standards established by the AI Solution Architect.
• Own agent reliability, observability, fallback behavior, and lifecycle management in production, keeping automations dependable as they scale.
• Direct coding agents to build enterprise-grade internal and external applications and services (dashboards, microservices) that operationalize and extend automation initiatives.
• Create and refine the AI prompts, agent skills, and context packages that drive automation quality, then monitor, troubleshoot, and optimize for accuracy, performance, and measurable business value.
• Partner with cross-functional stakeholders to identify and prioritize the automation opportunities that deliver the highest business impact.

Collaboration & Partnership

• 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 the AI Solution Architect to apply engineering-practice standards, governance, and metrics, and surface improvements from what you learn building in production.
• Work closely with the AI Verification Architect to make your work testable, building features against the verification frameworks and acceptance criteria that validate quality and behavior.
• Collaborate daily with engineering peers and the AI First Product team to refine specifications, resolve dependencies, and ship product increments that move agreed-upon metrics.
• Partner with citizen developers and engineering peers to share knowledge, reusable patterns, and AI First best practices, providing the guidance and insight their teams need to succeed.
• Follow responsible AI practices in everything you build: fairness, explainability, model monitoring, ethics, and regulatory alignment.

REQUIRED QUALIFICATIONS:


Core Experience

• 4-8 years of professional software engineering experience building and shipping production SaaS, including time as a senior developer or equivalent hands-on engineering role.
• Strong software engineering fundamentals: production-level, cloud-native development in the Microsoft stack (C#/.NET, React/TypeScript, RESTful Web APIs, SQL Server / Azure SQL) and familiarity with distributed-systems patterns such as queues, caching, and scalable APIs.
• Experience building, deploying, and maintaining production services through CI/CD, test-driven development, and rapid, iterative release cycles, not just prototypes.
• Proven AI First delivery record: production systems built and shipped using agentic workflows and spec-driven development, with demonstrable business outcomes.
• Hands-on experience designing and operating multi-agent systems, including orchestration, planning, and observability in production environments.
• Comfort owning features end to end, from specification through deployment and operation, and iterating based on measured outcomes.
• Excellent written and verbal communication skills; able to collaborate with product and business stakeholders and explain technical trade-offs to non-technical audiences.

AI & Claude Ecosystem Proficiency (Claude Strongly Preferred)

• Hands-on production experience with Claude Code as a primary development tool, including AI coding agents, agentic workflows, CLI-based development, and directing coding agents to ship production software.
• Prompt engineering skills, including context engineering, structured outputs, and retrieval-augmented prompting applied in production agent systems.
• Production experience with the Claude API: tool use, document processing, streaming, rate-limit management, and vision.
• Hands-on experience with multi-agent design patterns (planning, orchestration, observability) and building and consuming MCP servers that expose enterprise data sources as model-ready tools.
• Applied software engineering discipline in AI systems: version control, testing, and deployment pipelines for agent-based and model-dependent services; evaluation frameworks that measure AI quality, cost, and latency; and responsible-AI design aligned with Anthropic's principles.

HIGHLY DESIRED QUALIFICATIONS:

• Experience operating AI workflows in production, including agent observability and debugging live systems.
• Experience with Azure cloud infrastructure and integrations with major enterprise ERP and CRM systems.
• Bachelor's degree in Computer Science, Information Systems, or equivalent professional experience.