AI Product Engineer

JLL•Chicago, IL

4d•Remote

About The Position

JLL's Project & Development Services business line is building production AI capabilities for construction and real estate project delivery, and we need someone who thinks at a systems level. You're a solution developer, but you’re also an engineer who builds the infrastructure that makes AI solutions reliable, scalable, and maintainable. In this role you'll be responsible for the engineering layer underneath our AI-powered workflow tools: the extraction scripts, validation frameworks, output schemas, integration connectors, and quality harnesses that turn a capable AI model into a dependable production tool. You'll set engineering standards, make architectural decisions, and be the person others come to when a pipeline is misbehaving in a way nobody can explain.

Requirements

Strong Python proficiency: data parsing, file I/O, schema validation, subprocess management, packaging, and test authoring (pytest or similar)
Solid understanding of REST API design and consumption, including auth patterns (OAuth, API keys, token refresh), pagination, and error handling
Comfort with document parsing libraries: PyMuPDF, python-docx, openpyxl, pandas, and equivalent tools for common enterprise file formats
Experience with Git-based development workflows: branching, versioning, code review, and structured release management
Familiarity with enterprise integration surfaces, particularly Microsoft 365 (SharePoint, OneDrive, Graph API)
Hands-on experience building the code layer around LLM APIs: structuring prompts programmatically, managing token budgets, parsing and validating model outputs, and handling failure cases gracefully
Understanding of how structured context, schema-constrained outputs, and validation pipelines improve AI solution reliability in production
Familiarity with document chunking, embedding workflows, and retrieval patterns (RAG), including the tradeoffs between retrieval approaches for enterprise document types
Exposure to agentic patterns, multi-step reasoning pipelines, and tool use via MCP or similar protocols
Experience building test infrastructure for systems with probabilistic outputs: evaluation frameworks, regression suites, benchmark datasets
Comfort defining "correct" programmatically for outputs that don't have a single right answer, and building scoring logic that reflects domain standards
Instinct for failure modes: silent errors, schema drift, edge-case documents, and model-version-induced regressions
You’ve built something from scratch specifically to understand how it worked
You're comfortable making principled decisions in the absence of established conventions, and you document those decisions so the next person understands the reasoning
You hold your technical opinions firmly enough to be useful and loosely enough to update them
You're energized by fields where the tooling is still being invented and you can influence how it develops
Candidates must be authorized to work in the United States without sponsorship.

Nice To Haves

Experience in or meaningful exposure to construction, commercial real estate, or professional services environments is a plus
Prior work in a technical role at a professional services firm, PropTech company, or enterprise software organization is relevant background

Responsibilities

Working With Real-World Data: Develop deep familiarity with the information landscape of construction and real estate project delivery, understanding what data exists, where it lives, what form it takes, and what has to happen before an AI model can do something useful with it.
Output Design and Quality Assurance: Design the structured output contracts that govern what AI solutions produce and build the validation logic that enforces them. Own the detection and recovery logic when a solution produces unexpected output or degrades silently on an unusual document. Define what production-ready looks like before building begins, run solutions against diverse real-world document sets, and maintain quality as the underlying models and input corpus evolve over time.
Enterprise System Integration: Connect AI solutions to JLL's enterprise environment using REST APIs, Microsoft Graph, SharePoint, OneDrive, and other standard integration surfaces. Handle authentication lifecycle, retry logic, rate limits, and the realities of operating inside an enterprise network with real access controls. Design integrations that are resilient and maintainable.
Agentic Architecture and MCP Integration: Design and build multi-step reasoning pipelines that connect models to enterprise tools and data through the Model Context Protocol and similar agentic infrastructure. Think carefully about how to structure tool availability, manage context across steps, and build agent workflows that are reliable and auditable. Stay current on how this space is evolving and bring informed opinions about when agentic patterns are the right approach and when they aren't.
Platform Engineering and Standards: Establish and maintain the engineering patterns others follow: packaging conventions, versioning, configuration management, logging, and error handling. Write internal tooling that makes building new solutions faster and less error-prone, and make architectural decisions that hold up as the team and codebase scale.