Senior Software Engineer (San Francisco)

JLL empowers you to shape a brighter way. Our people at JLL are shaping the future of real estate for a better world by combining world class services, advisory and technology for our clients. We are committed to hiring the best, most talented people and empowering them to thrive, grow meaningful careers and to find a place where they belong. Whether you’ve got deep experience in commercial real estate, skilled trades or technology, or you’re looking to apply your relevant experience to a new industry, join our team as we help shape a brighter way forward. About the RoleAs a Staff Software Engineer on the MarTech Engineering Team, you'll be a forward deployed engineer embedded in the marketing organization, building production AI agents that solve real campaign, content, social, ABM, and performance problems. You'll work shoulder-to-shoulder with marketing domain experts (SMEs) — sitting in their workflows, learning their systems, and turning their expertise into agents that go live and stay live.Your remit spans the full lifecycle: rapid prototyping with SMEs to validate ideas, building the integrations and skills needed to ship a working pilot, and hardening pilots into production-grade agents that operate reliably at scale. When something is missing — a CRM that doesn't expose what you need, a data source not yet in the warehouse, a guardrail that doesn't exist — you'll either build a pragmatic workaround to unblock the pilot or translate the gap into a clear, prioritized requirement for our partner platform team — the engineers who own the underlying marketing systems, data plumbing, and AI-native tooling — to address. You sit at the seam between domain expertise and platform infrastructure, and your job is to make sure neither side waits on the other.The role demands deep technical judgment: when to build vs. wait, when to abstract a one-off solution into a reusable skill, and how to ensure agent outputs translate into safe, brand-aligned, and factually correct actions across a complex marketing stack. Success is measured by the volume and quality of marketing work that agents are actually doing in production — not by demos, not by POCs, but by agents that marketers trust to do the job. This is a fantastic opportunity to build the agentic layer of one of the world's largest commercial real estate platforms from the ground up, and to see your work change how marketing operates at global scale.Who You AreWe're optimizing for three things ahead of tool-specific experience: deep technical fundamentals, a pragmatic problem-solving disposition, and exceptional cross-audience communication. The agent tooling landscape changes every few months — what we can't easily teach is how someone thinks, ships, and explains under uncertainty. If you have those three, we'll happily back you while you skill up on whichever runtime, framework, or model provider this quarter favors.You have a Bachelor's or Master's degree in Computer Science, Engineering, or a related field, or equivalent work experienceYou are proficient in English, both written and verbal, sufficient for success in a remote and largely asynchronous work environmentYou have 5+ years of software engineering experience working in production systems, including significant time integrating against enterprise APIs (CRMs, CMSes, DAMs, ad platforms, marketing automation tools, analytics)You have hands-on experience with modern LLM APIs across providers — including prompt engineering, tool use / function calling, structured outputs, and context engineering — and you've worked with enough of them to know that the underlying patterns transfer even as the specific APIs evolveYou have experience designing agent systems: multi-step reasoning, tool orchestration, memory, error recovery, and human-in-the-loop escalation pathsYou've worked through the hard parts of agent engineering firsthand — hallucination grounding, tool reliability and silent failures, evals that actually predict real-world behavior (and the gap when they don't), cost and latency tradeoffs, prompt drift, and the difference between works in a demo and still works on day 30. You can talk concretely about what you've tried, what's broken on you, and what you've learned. We care more about depth of engagement with these problems than years loggedYou have experience building RAG systems — embeddings, vector stores, retrieval optimization, and grounding — and a strong intuition for when retrieval is the right answer vs. when a tool call, fine-tune, or schema change is the better leverYou've deployed LLM-powered services or agents to production cloud environments and understand the operational reality — auth, networking, secrets, observability, rollback, cost monitoring — beyond the demo-day setup. The specific runtime matters less to us than the fact that you've operated something live and learned from itYou're energized by embedding directly with non-technical domain experts, can translate vague problem statements into shippable scope, and have the patience to learn an unfamiliar domain (marketing, in this case) deeply enough to anticipate where agents will failYou have a pragmatic bias for shipping — you can tell when a brittle workaround is the right call to unblock a pilot and when something deserves to be built right the first timeYou translate fluently between technical levels — from explaining agent failure modes to a non-technical marketing SME, to briefing leadership on architectural tradeoffs without dumbing them down, to going deep on protocol details with platform engineers, often within the same day. This skill weighs as heavily for us as your technical depthYou have strong analytical and interpersonal skills, with a proven ability to thrive and collaborate in dynamic, product-focused, distributed teamsYou embrace a proactive approach to problem-solving and a willingness to acquire new skills and knowledge as needed to achieve resultsYou're confident taking ownership of projects from start to finish and enjoy turning nebulous ideas into realityYou make your coworkers feel included in every interactionWhat You'll DoEmbed with marketing SMEs across campaigns, property marketing, content production, social, ABM, and performance intelligence to design and ship agents that do real work in their day-to-dayBuild, deploy, and operate production marketing AI agents that reason over regional context, brand guidelines, and intent data — and invoke tools to draft content, configure campaigns, monitor performance, and recommend optimizationsDesign and grow the Marketing Domain Skills Library — composable LLM workflows (drafting, scoring, classification, brand-voice tuning) extracted from live agent work as reusable primitives that multiple agents can callBuild integrations against marketing systems (CMS, DAM, CRM, marketing automation, ad platforms, analytics) — directly when needed to unblock a pilot, and through Marketing MCP servers built by that platform team once those existTranslate integration and capability gaps you hit during pilots into clear, prioritized requirements for the platform team, so the platform layer evolves to meet real agent needs rather than speculative onesOwn reliability, observability, evaluation, and cost efficiency of LLM-powered workflows in production — including brand-voice checks, factual grounding against property and client data, regression suites, and offline benchmarks wired into CI/CDDesign multi-agent orchestration patterns: how the Campaigns agent coordinates with Social, ABM, Content, Property, and Performance Intelligence; where to compose vs. where to keep boundaries; how escalations and handoffs flowSet the bar for the agent pod: define the playbook for going from SME conversation to working pilot to deployed prod agent, and raise the technical quality of what the team shipsRepresent MarTech Engineering externally — to JLL leadership, to customers, and in the broader engineering community — as a credible voice on building agents that actually work in productionPublish what you learn — internal write-ups, engineering blog posts, and conference talks. Forward deployed agent work surfaces novel problems and solutions every week, and externalizing them sharpens the team's thinking, raises our hiring bar, and contributes back to the broader agent engineering communityStay at the frontier of agent engineering and bring the best ideas back to the team, continuously raising the bar on quality, performance, and architecture at scaleDrive innovation with a willingness to experiment and to boldly confront problems of immense complexity and scopeThis position does not provide visa sponsorship. Candidates must be authorized to work in the United States without sponsorship.Estimated compensation for this position:200,000.00 – 250,000.00 USD per yearThis range is an estimate and actual compensation may differ. Final compensation packages are determined by various considerations including but not limited to candidate qualifications, location, market conditions, and internal considerations.Location:On-site –Chicago, IL, San Francisco, CAIf this job description resonates with you, we encourage you to apply, even if you don’t meet all the requirements. We’re interested in getting to know you and what you bring to the table!Personalized benefits that support personal well-being and growth:JLL recognizes the impact that the workplace can have on your wellness, so we offer a supportive culture and comprehensive benefits package that prioritizes mental, physical and emotional health. Some of these benefits may include:401(k) plan with matching company contributionsComprehensive Medical, Dental & Vision CarePaid parental leave at 100% of salary Paid Time Off and Company HolidaysEarly access to earned wages through Daily PayAt JLL, we harness the power of artificia