Applied AI Engineering Lead

Thresh Consulting; Chicago (IL); Hybrid; USD 190,000 - 235,000; Full time

Job summary

Thresh Consulting is seeking an Applied AI Engineering Lead to shape and ship production AI systems for clients. You will own technical direction, architect end‑to‑end LLM solutions, and guide a 2–4 engineer team across front‑end, APIs, data, and cloud.

This role blends hands‑on build with leadership in a hybrid setting. You will focus on trusted AI, guardrails, evaluation, and cost/latency tradeoffs, while partnering with client engineering leaders and Thresh practice leads to scope new AI

Qualifications

• 7+ years building production software with 2+ years in LLM powered products.
• Strong React, TS, and Next.js for production UI work.
• Experience with MCP servers or similar tool‑integration layers.

Responsibilities

• Set technical direction for AI engagements and client scoping.
• Architect end‑to‑end LLM solutions and evaluate calls.
• Lead a small engineering team and mentor peers.
• Build AI‑powered, customer‑facing experiences and guardrails.

Skills

LLM engineering

React & TS

Next.js

API design

MCP servers

Vector search

Prompting frameworks

Tools

OpenAI API

Claude

LangGraph

PostgreSQL

NoSQL

Docker

AWS Bedrock

Azure OpenAI

Google Vertex AI

Job description

About the job

APPLIED AI ENGINEERING LEAD

Thresh Consulting — Strategy in Action for the AI Era

Salary: $190,000 – $235,000 + up to 25% performance-based bonus

Location: Hybrid (Denver, Chicago, or NYC preferred)

ABOUT THRESH

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.

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.

ROLE OVERVIEW

The Applied AI Engineering Lead turns ambition into production systems that move a client's business. You'll own the technical direction of our AI engagements: deciding which problems are worth solving with AI, architecting the solution, and leading the team that ships it. Your depth is in applied LLM engineering: agents, tool use, retrieval, evaluation, and the guardrails that make AI safe to put in front of customers. You're fluent enough across front end, APIs, data, and cloud to build an experience end-to-end yourself when it counts.

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. You'll also work with Thresh's practice leads to scope and shape new AI work.

WHAT YOU'LL DO

Set technical direction for AI engagements

• Partner with clients to identify and prioritize high-value AI use cases, and be clear about what's ready for production versus what's still a demo.
• Architect end-to-end LLM solutions: model selection, prompting strategy, retrieval, agents and tool use, and the integrations that connect them to real systems.
• Make build, buy, prompt, or fine-tune calls based on cost, latency, quality, and risk, and explain those calls to client leadership.
• Shape scope, estimates, and technical approach for new AI engagements alongside Thresh's practice and sales leads.

Build AI-powered, customer-facing experiences

• Build conversational shopping experiences where customers discover, compare, and buy through natural language, from first question to completed order.
• Set the patterns for streaming interfaces that stay fast and readable under real load, including partial responses, tool-call states, errors, and graceful fallbacks.
• Bring real business logic into the conversation: live pricing, inventory, promotions, personalization, and customer account context.

Build agents, tools, and integrations

• Build for a client's own site and app and for third-party AI assistants like ChatGPT and Gemini, all from one shared foundation.
• Build and extend MCP servers and tools that give models safe, structured access to catalog, pricing, cart, and order capabilities.
• 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.
• Work with emerging agentic commerce protocols (ACP, UCP), and know where each fits a client's business model.
• Integrate with enterprise commerce, catalog, order, and identity systems that were never designed for AI.
• Design multi‑step agents and workflows that take real actions in client systems, with clear permissions, human‑in‑the‑loop checkpoints, and audit trails.
• Build retrieval and knowledge systems (RAG) over client content, catalogs, and documentation, and tune them for accuracy.

Make AI trustworthy in production

• 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.
• Own the evaluation strategy. Build eval sets and automated test harnesses covering clean queries, edge cases, out‑of‑scope requests, and prompt‑injection attempts, and turn what you find into fixes and release gates.
• Instrument conversations end to end for analytics, attribution, observability, cost, and latency, so clients can measure what the experience drives.
• Prepare work for the legal, privacy, security, and brand reviews that every transactional AI experience goes through.
• Monitor model quality, drift, and spend after launch, and plan for model upgrades and vendor changes without breaking the experience.

Champion Agentic Development

• Make AI coding agents (Claude Code, Cursor) your default way of working.
• Write specs precise enough for an agent to implement against, then verify the output against the spec rather than the diff.
• Prototype conversational features in days with mock data, so clients can see the experience before the real integrations land.
• Test new tools and workflows, and bring what works back to the team and to the wider Thresh practice.

Lead and elevate

• Mentor engineers through code review, pairing, and technical guidance, across the full applied AI stack, from prompting and evals to production architecture.
• Partner with product managers and designers on conversation design, scope, technical risk, and estimates.
• Define the components, patterns, and standards that become reusable assets across Thresh's AI work, including reference architectures and starter kits.
• Help build Thresh's applied AI capability through hiring input, technical interviews, and internal enablement.
• Represent Thresh's AI point of view with clients and platform partners through workshops, technical content, and pre‑sales conversations.

Deliver for clients

Own AI solutions from discovery through production deployment.

Explain progress and tradeoffs clearly to technical and non‑technical stakeholders, including what AI can and can't reliably do.

Work within each client's existing stack, frameworks, and constraints.

Hold the quality bar when deadlines tighten and requirements shift.

WHAT YOU BRING

Technical

• 7+ years building and shipping production software, including 2+ years shipping LLM‑powered products to real users.
• Strong working knowledge of React, TypeScript, and Next.js enough to build, review, and guide production UI work.
• Shipped streaming or conversational UI in production, including tool‑calling patterns and structured model output.
• Experience building or consuming MCP servers, or a comparable tool‑integration layer for LLMs.
• Deep, hands‑on experience with LLM APIs and agent frameworks (e.g., Claude, OpenAI, Gemini; agent SDKs, LangGraph, or similar), including prompting, tool use, structured output, and multi‑step agents.
• Built retrieval‑augmented systems in production, including embeddings, chunking, vector or hybrid search, and accuracy tuning.
• Designed and run LLM evaluation frameworks, and used the results to make shipping decisions.
• Practical understanding of LLM security and risk: prompt injection, data leakage, PII handling, and responsible AI practices.
• Can reason about model cost, latency, and quality tradeoffs, and make model selection calls that hold up.
• Strong back‑end skills in Python and/or Node.js. You can design and build the services and APIs your AI systems need.
• API experience across REST and/or GraphQL, plus working fluency with PostgreSQL and NoSQL stores.
• Working knowledge of cloud platforms and their AI services (e.g., AWS Bedrock, Azure OpenAI, Google Vertex AI), CI/CD, and Docker.
• Daily, hands‑on use of AI coding agents in real work. Be ready to show us how you use them.
• Bonus: e‑commerce, checkout, or payments experience in a high‑volume environment.
• Bonus: fine‑tuning, classical ML, or data engineering experience for when a problem calls for it.

How you work

• You ship production systems on time and at a high standard.
• You do well when requirements evolve and priorities shift.
• You debug across layers, propose fixes, and make pragmatic tradeoffs.
• You know when is the right call and when to push for excellence.
• You care about the details users notice, and the ones they don't.
• You've led technical teams through delivery and helped other engineers grow
• You explain technical concepts to non‑engineers clearly.
• You can tell a client when AI isn't the right answer, and explain why.
• Client‑facing or professional services experience is strongly preferred.

WHY THRESH

• Senior-level competitive compensation with performance bonus upside.
• Comprehensive healthcare benefits.
• 401(k) with company matching.
• High ownership and influence over technical direction of Thresh's AI practice.
• Hybrid delivery flexibility with client travel and team co‑locations.
• A low‑ego culture built on clarity, craft, and outcomes.