Senior AI Engineer in Mundelein

You’ll spend about 70% of your time building and 30% leading. You’ll guide a team of 2-4 engineers, and serve as a primary partner to client engineering leaders., * Deep expertise in React, TypeScript, and Next.js, including state management, rendering strategies, and application architecture. \n

• Shipped streaming or conversational UI in production, including tool-calling patterns and structured model output. \n

• Experience building or consuming MCP servers, or a comparable tool-integration layer for LLMs. \n

• Hands-on experience building or scaling a design system and component library. \n

• Mastery of HTML, CSS, and responsive design, with working knowledge of WCAG accessibility standards. \n

• A track record of measurable front-end performance work. \n

• Solid back-end skills in Node.js, Python, or a comparable ecosystem. You can design and build the APIs your UI needs. \n

• API experience across REST and/or GraphQL, plus working fluency with PostgreSQL and NoSQL stores. \n

• Working knowledge of cloud platforms, CI/CD, and Docker. \n

• Comfort working in other frameworks, such as Angular or Vue, when a client’s stack calls for it. \n

• Daily, hands-on use of AI coding agents in real work. Be ready to show us how you use them. \n

• Bonus: e-commerce, checkout, or payments experience in a high-volume environment. \n

The Senior AI Engineer builds the experiences customers actually touch, and the services behind them. Your depth is on the front end: React architecture, design systems, performance, and accessibility. You’re fluent enough across APIs, data, and cloud to ship a feature end-to-end without waiting on anyone.

n \n

• Build conversational shopping experiences where customers discover, compare, and buy through natural , from first question to completed order. \n

• Render rich, branded UI inside the conversation, such as product cards, comparisons, configurators, carts, and checkout steps that the model calls as tools and the frontend draws in real-time. \n

• Build streaming interfaces that stay fast and readable under real load, including partial responses, tool-call states, errors, and graceful fallbacks. \n

• Bring real business logic into the conversation: live pricing, inventory, promotions, personalization, and customer account context. \n

• Extend a client’s design system into an AI component library, so conversational surfaces look and behave like the rest of the brand. \n

\n

\n

Ship one experience across many surfaces

\n

\n \n

• Build for a client’s own site and app and for third-party AI assistants like ChatGPT and Gemini, all from one shared foundation. \n

• Build and extend MCP servers and tools that give models safe, structured access to catalog, pricing, cart, and order capabilities. \n

• Prepare commerce systems for AI agents that shop on a customer’s behalf, with structured product data, agent-ready checkout, and clear rules for what an agent can and can’t do. \n

• Work with emerging agentic commerce protocols (ACP, UCP), and know where each fits a client’s business model. \n

• Integrate with enterprise commerce, catalog, order, and systems that were never designed for AI. \n

\n

\n

Make AI trustworthy in production

\n

\n \n

• Build guardrails that keep the assistant in scope. That means no fabricated prices, promises, or commitments, and a clean handoff to a person or standard flow when a request goes past what it should handle. \n

• Test against clean queries, edge cases, out-of-scope requests, and prompt-injection attempts, and turn what you find into fixes. \n

• Instrument conversations end to end for analytics, attribution, and observability, so clients can measure what the experience drives. \n

• Prepare work for the legal, privacy, security, and brand reviews that every transactional AI experience goes through. \n

\n

\n

Build with AI agents

\n

\n \n

• Make AI coding agents (Claude Code, Cursor) your default way of working. \n

• Write specs precise enough for an agent to implement against, then verify the output against the spec rather than the diff. \n

• Prototype conversational features in days with mock data, so clients can see the experience before the real integrations land. \n

• Test new tools and workflows, and bring what works back to the team. \n

\n

\n

Lead and elevate

\n

\n \n

• Mentor engineers through code review, pairing, and technical guidance, with a focus on front-end craft. \n

• Partner with product managers and designers on conversation design, scope, technical risk, and estimates. \n

• Contribute components, patterns, and standards that become reusable assets across Thresh’s AI commerce work.

Thresh Consulting is a modern digital consulting firm built for the AI era-where strategy, execution, and craft come together to deliver real outcomes with speed. Our specialty is helping organizations design, build, and scale digital products that create exceptional customer experiences and drive value.

\n

\n

Our engineers are builders who work side by side with product & design. We value clarity over complexity, quality over shortcuts, and learning as a core part of growth.