Agentic AI Engineer

Agentic AI Engineer

Envorso Sports

Seattle, WA (Hybrid) · Full-time

You'll build the agents that turn a pro sports team's ticketing and fan data into revenue: one that catches a stale cart and proposes a win-back offer, another that hands a marketer a segment they can act on without waiting on an analyst. Then you'll ship the web and mobile surfaces that put that work in front of fans.

Envorso Sports runs a professional sports team's entire fan-facing business from one platform instead of six stitched-together vendors: ticketing, website, and mobile app today, with commerce, CRM, and marketing automation on the near-term roadmap. It's live in production right now with the Seattle Seawolves of Major League Rugby, and expansion is planned across the league and into other pro sports organizations.

This role scales the platform two ways: as a product capability and as how the engineering team builds. On the product side, you'll design agentic features that act on fan and ticketing data, fan scoring, segmentation, and an offers engine that proposes campaigns instead of reporting on what fans did. On the engineering side, you'll build and own the internal agent tooling: guardrails on what coding agents can touch, PR-review agents that check against the spec, and automated checks that keep frontend and backend in sync as API contracts change. You'll set the standard the rest of the team works against. Because of the stage, this isn't backend-only: you'll ship the front-end on web (Next.js) and mobile so your agent work reaches fans and marketers, not just an API. You'll own the full lifecycle, from design and evaluation through deployment, monitoring, and iteration, with no ML platform team to hand off to. You'll report into product and work daily with a tech lead and engineering team mostly based in Argentina, so expect overlap-hours collaboration.

You fit if you bring 3+ years of software engineering with at least a year building and shipping AI/LLM-powered applications in production, not a prototype that never left a notebook, and you're strong in TypeScript and comfortable in both a Next.js app and an API-service codebase (Python is a plus). You've done multi-agent design, tool use, memory, and orchestration, not a single prompt-and-response wrapper, and you're full-stack enough to ship a feature end to end, including the web UI and ideally the mobile UI that surfaces it. The builders who do well here can explain what an agent is doing, where it breaks, and why, to a product person or a non-ML engineer, and they're comfortable deciding what the right thing to build is rather than waiting for a fully scoped ticket. You must be authorized to work in the US; Envorso is not sponsoring visas for this role.