About The Team We are building JLL's internal AI platform: the layer every team in the firm uses to ship AI agents and AI-backed products. That means a gateway that puts a large and growing set of models from multiple providers behind one API, a shared chat surface that makes any agent reachable by employees across the firm, the developer tooling that takes an agent from an idea to something running in production, etc.

Dozens of applications across JLL already run on the platform, with more being moved onto it. When one of the teams behind them gets stuck, whether it is an expired token deep inside an agent run, a model call failing at the gateway, or an MCP server that works locally and not in production, the engineers in these roles are the ones who get them moving again, and then make sure the next team never hits the same wall.

About The Role We are hiring Senior Software Engineers to own how the platform supports the teams building on it. This is a deeply technical role. The problems that reach you are the ones another team could not solve on their own, and they cross every boundary at once: identity, networking, cloud permissions, model APIs, MCP servers, agent runtimes, deployment.

The job is not to close tickets. It is to understand why a team's agent environment is failing, fix it, and then remove the cause so the problem never recurs, through better diagnostics, better documentation, self-service tooling, or a change to the platform itself. Engineers in this role also ship features on the platform backlog.

What You'll Do Support the teams building agents on the platform

- Own the support queue: triage, resolve and escalate requests from teams across the firm, and see each one through to resolution




- Debug across the full path of an agent in production: identity and token lifecycle, gateway calls, MCP servers, agent runtimes, networking, secrets, deployment
- Reproduce what a team is seeing in their environment, find the real cause, and either fix it or get it fixed
- Coordinate during incidents: bring in application owners, keep stakeholders informed, and keep the engineers working the fix uninterrupted

Engineer the support load down

- Consolidate the several channels requests reach us through today into one clear path, with the triage and escalation model to go with it
- Turn recurring problems into runbooks, diagnostics and self-service, so the next team never needs to ask
- Write the integration guides, reference implementations and starter templates that teams building agents and MCP servers actually use
- Hunt down the undocumented limits, misleading error messages and missing guardrails that generate tickets, and fix them at the source
- Help consuming applications move onto the gateway as the migration progresses

Build the platform

- Ship features on the platform backlog alongside support work: gateway, agent tooling, identity patterns, observability, etc.
- Share production ownership with the rest of the team, including incident response and root cause analysis

Required What we're looking for

- 5+ years building and operating production systems




- Strong debugging across distributed systems: you can trace a failure through identity, network, API and runtime boundaries and explain what happened
- Hands-on experience with at least one major public cloud, including IAM, networking and secrets management in production
- Hands-on experience building or operating an MCP server or a production agent, and a solid understanding of how LLM applications are put together: model APIs, tool calling, agent frameworks, etc.
- Experience supporting other engineering teams as the users of your work, with the patience and clarity that requires
- A bias toward removing whole classes of problems rather than resolving them one at a time
- Excellent English communication, written and spoken

Preferred

- Identity and access depth: OAuth 2.0, OIDC, token exchange, service principals
- Kubernetes and container-based delivery
- Infrastructure as code
- Observability tooling and production alerting
- Prior experience in a developer support, platform enablement or SRE role

How we work: you should be comfortable with

- A small team that moves quickly inside a very large organisation
- Limited timezone overlap with some of your teammates
- A platform with production users while it is still being built underneath them
- Being interrupted by other teams and by production, and still shipping

What We Offer

- A front row seat to how every team at JLL builds with AI, and a hand in whether they succeed
- Real technical breadth: gateway, agent runtimes, MCP, identity, cloud infrastructure
- A role that grows into platform engineering by design: the support work you remove becomes time you spend building
- A team spanning the Americas, EMEA and APAC

📌 Senior Software Engineer, AI Platform Enablement (Jalisco)
🏢 Jll
📍 Jalisco