Staff Software Engineer, AI Platform

JLL•Chicago, IL

1d•$160,000 - $260,000•Remote

About The Position

We are building JLL's internal AI platform: the layer every team in the firm uses to ship AI agents and AI-backed products. This includes a gateway that provides a unified API for a large and growing set of models from multiple providers, a shared chat surface for firm-wide agent accessibility, and developer tooling for deploying agents from concept to production. You will join early enough to shape the platform's future. The foundations are live and handling production traffic, and the decisions made now will determine how every team at JLL builds with AI. This role offers a unique opportunity to set technical direction at a large firm and see the impact of your work across the business quickly.

Requirements

8+ years building and operating production systems.
Direct experience shipping agentic systems to production (agentic patterns, retrieval, tool calling, inference cost and latency, etc.).
Hands-on experience with more than one model provider, including managing differences between them.
Experience with evaluation, observability, or guardrail tooling for agentic systems.
Strong platform engineering track record, with experience supporting other engineering teams as users.
Hands-on depth in at least one major public cloud, including running and debugging production workloads.
Experience designing stable APIs and abstractions for others to build upon.
Demonstrable production ownership, including on-call, incident response, and root cause analysis.
A track record of driving initiatives through large organizations, navigating processes, and unblocking decisions.
Excellent English communication, written and spoken.

Nice To Haves

Built or operated an internal developer platform or shared multi-tenant service.
Kubernetes and container-based delivery.
Infrastructure as code.
Enterprise security, data privacy, or responsible-AI review processes.

Responsibilities

Build the platform, owning significant parts end-to-end, from API design to performance under load.
Be accountable for the reliability and performance of the platform's gateway, which is critical for all AI-driven firm initiatives.
Design the model gateway, including provider abstraction, routing, failover, and enabling provider switching through configuration.
Ensure the agent surface functions regardless of the framework or deployment location chosen by a team.
Solve AI engineering challenges, including building evaluation and benchmarking capabilities from scratch.
Design and implement guardrails for safe production deployment of agents, translating internal standards into enforceable code.
Own inference cost and latency as primary engineering concerns, including spend attribution and routing decisions.
Keep pace with the rapidly changing model landscape and establish a routine process for onboarding new models.
Set the standard by making the compliant path the fastest path, ensuring platform usage aligns with architecture, security, and responsible AI reviews.
Serve as the go-to engineer for other teams facing complex integration problems.
Enhance observability before scale necessitates it.
Mentor engineers across a distributed team and create lasting designs and documentation.