Forward Deployed Engineer

JLL•Chicago, IL

2d•$280,000 - $300,000•Onsite

About The Position

As a Forward Deployed Engineer, you will operate at the front lines of innovation — embedded directly with subject matter experts, product, and engineering teams to rapidly design, architect, prototype, and deploy solutions that solve high-priority business problems. This is not a traditional engineering role with long delivery cycles. You will be expected to go from concept to working prototype in days, not months, while maintaining enterprise-grade standards for quality, security, and scalability. You bring an exceptional combination of skills: deep hands-on engineering experience across AI agents and full-stack development, and the interpersonal skills to earn trust, drive alignment, and influence without authority. You are equally comfortable whiteboarding a system architecture with senior stakeholders and writing production code the same afternoon. You have direct experience developing agents on platforms like AWS Agent Core, and you thrive in fast, ambiguous environments where creative thinking and execution speed matter.

Requirements

8+ years of professional software engineering experience, including solution design and architecture ownership
Demonstrated ability to architect end-to-end systems — from requirements through deployment — with clear documentation and stakeholder communication
Hands-on experience building AI agents, including defining agent skills, tool use, memory, and multi-step reasoning
Experience with AI-Augmented Engineering (Harness Engineering) — actively use tools like Claude Code, Codex, or equivalent assistants to accelerate coding, documentation, and problem-solving day-to-day.
Direct experience with AWS Agent Core or equivalent — building, deploying, and operating agents in production
Working knowledge of Model Context Protocol (MCP) — including building or consuming MCP servers to connect agents with external systems
Experience with agentic frameworks such as LangChain, LangGraph, AutoGen, CrewAI, or Semantic Kernel
Proficiency in Python and at least one front-end framework (React, Vue.js, or Angular)
Experience with cloud platforms (AWS, Azure, or GCP)
Exceptional communication and interpersonal skills — you can earn trust quickly, navigate ambiguity, and drive alignment across diverse teams
Comfort working in fast-paced environments with shifting priorities and high ownership expectations
Candidates must be authorized to work in the United States without sponsorship.

Nice To Haves

Experience with RAG architectures, vector databases (Pinecone, Weaviate, pgvector), and semantic search
Familiarity with prompt engineering, fine-tuning, and LLM evaluation techniques
Experience with agent observability and tracing tools (LangSmith, Arize, Weights & Biases, or similar)
Experience with containerization and CI/CD practices (Docker, Kubernetes, GitHub Actions)
Background in real estate, financial services, or other data-intensive enterprise domains
Experience facilitating technical discovery workshops, design sprints, or architecture reviews

Responsibilities

Lead solution design for complex, cross-functional data and AI problems — from initial discovery through to technical blueprint
Define and communicate architecture decisions, trade-offs, and delivery approaches to both technical and non-technical audiences
Design scalable, modular systems that balance the need for speed with enterprise standards for reliability, security, and maintainability
Participate in architecture reviews, ensuring alignment with enterprise patterns and platform standards
Create clear technical documentation: architecture diagrams, data flow maps, API contracts, and solution briefs
Design and deliver working prototypes for complex data and AI problems within compressed timeframes, often days to weeks
Translate ambiguous business requirements into concrete technical solutions with minimal hand-holding
Balance speed of delivery with enterprise standards — your prototypes are production-ready, not throwaway
Continuously iterate on solutions based on direct feedback from product managers, program leads, and end users
Develop intuitive front-end interfaces and dashboards that bring data and AI outputs to life for business users
Apply strong UX instincts to simplify complex flows and make agent outputs accessible and actionable for non-technical stakeholders
Design, build, and deploy AI agents and multi-agent systems that automate complex workflows end-to-end
Develop and maintain agent skills — discrete, reusable capabilities that compose into larger agentic pipelines
Implement and extend Model Context Protocol (MCP) servers and clients to connect AI agents with enterprise tools, APIs, and data sources
Design evaluation harnesses, guardrails, and monitoring pipelines to ensure agent reliability and safety in production
Stay current with the rapidly evolving agentic AI landscape and proactively introduce new techniques and tooling to the team
Integrate LLMs, RAG systems, and ML models into production workflows
Embed directly with product, program, and engineering teams to co-define problems and co-deliver solutions
Influence technical direction and build alignment across teams without relying on formal authority
Communicate complex technical concepts clearly to non-technical business stakeholders — in writing, in meetings, and in executive presentations
Mentor and elevate junior engineers, sharing patterns and practices for agentic development, prompt design, and rapid delivery
Foster a collaborative, low-ego team culture where speed and quality go hand in hand