Staff Software Engineer, AI Platform

JLL•Chicago, CO

1d•Remote

About The Position

JLL is building its internal AI platform, which will serve as the central layer for all teams within the firm to develop and deploy AI agents and AI-backed products. This platform will provide a unified API for a wide range of models from multiple providers, a shared chat interface for firm-wide agent accessibility, and developer tools to streamline the agent development lifecycle from concept to production. As an early member of this team, you will have a significant impact on shaping the future direction of this platform. The foundational elements are already in place and handling production traffic, and the upcoming decisions will define how every team at JLL leverages AI. This role offers a unique opportunity to influence AI strategy at a large firm and see the impact of your work across the business rapidly.

Requirements

8+ years of experience building and operating production systems.
Direct experience shipping agentic systems to production (not just prototypes), including agentic patterns, retrieval, tool calling, inference cost, and latency.
Hands-on experience with multiple model providers, understanding their practical differences.
Experience with evaluation, observability, or guardrail tooling for agentic systems.
Strong platform engineering background with experience supporting other engineering teams as users.
Hands-on expertise in at least one major public cloud, including running and debugging production workloads.
Experience designing APIs and abstractions that are stable and used by others.
Demonstrable production ownership, including on-call, incident response, and root cause analysis.
Proven ability to drive work through a large organization, navigating processes, influencing decisions, and unblocking progress.
Excellent English communication skills, both written and spoken.

Nice To Haves

Experience building or operating an internal developer platform or shared multi-tenant service.
Experience with Kubernetes and container-based delivery.
Experience with Infrastructure as Code.
Experience with 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 mechanisms, and ensuring provider switches can be handled via configuration.
Ensure the agent surface functions seamlessly regardless of the framework or deployment location of a team's agent.
Solve AI engineering challenges, including building evaluation and benchmarking capabilities from scratch.
Design and implement guardrails for safe agent deployment into production and enforce internal standards through code.
Manage inference cost and latency as primary engineering concerns, including spend attribution and routing decisions.
Adapt to the rapidly evolving model landscape by making new model onboarding a routine process.
Establish the platform as the compliant path, ensuring that building on the platform facilitates architectural, security, and responsible-AI reviews.
Serve as the go-to engineer for other teams facing complex integration challenges.
Enhance observability before scaling necessitates it.
Mentor members of a distributed team and create lasting designs and documentation.