Senior Applied AI Engineer
Let’s Tango! Where Innovation Meets Impact.
At Tango Analytics, we’re all about helping businesses make smarter decisions through powerful technology, insightful data, and a whole lot of collaboration. Whether you're a creative thinker, a strategic planner, a tech wizard, or a customer champion, there's a place for you on our team. We believe work should be meaningful and fun - so if you're ready to make a difference while enjoying the journey, come join us and let's Tango!
Role Summary:
We are looking for a Senior Applied AI Engineer to help build and ship Tango’s first AI-powered product, marking an important next chapter after 18 years as an industry leader in real estate technology.
In this highly hands-on role, you will turn advances in generative AI and machine learning into reliable, production-ready capabilities that solve meaningful problems for our customers. You’ll work closely with Product, Engineering, and domain experts to identify high-value use cases, rapidly prototype solutions, evaluate approaches, and take the best ideas all the way into production.
This is an opportunity to help establish how AI is built and applied at Tango from the ground up. You’ll influence technical architecture, engineering standards, evaluation practices, and product strategy while tackling complex, data-rich workflows across corporate real estate, workplace management, lease administration, and retail location management.
Key Responsibilities:
Agent Design & Delivery
Design, build, and ship production AI agents on LangGraph, keeping the agent layer portable across cloud platforms.
Own agents end to end: graph design, tool definitions, prompt and context engineering, durable execution, failure and retry behavior, and cost and latency budgets.
Build agent tooling against internal systems over MCP, using direct API calls where those are the better fit, and agent-to-agent interfaces as agents begin to compose.
Deliver human-in-the-loop review flows, including interrupt points, confidence surfacing, and the correction paths that let a customer review and override agent output.
Build and tune retrieval, covering chunking, hybrid retrieval, grounding, and citation back to source page and paragraph.
Evaluation, Quality & Trust
Contribute the evaluations for the agents you ship: golden datasets, LLM-as-judge and deterministic scorers, and regression suites that run in CI, built against the shared evaluation harness the platform provides.
Diagnose quality failures to root cause, whether retrieval miss, prompt defect, tool error, model regression, or flawed ground truth, and correct the appropriate layer.