Philadelphia, PAremote

Salary
—
Posted
Aug 5, 2026
Location
Philadelphia, PA
Last confirmed open
Sep 24, 2026

What this job asks for AI summary

This role at Nuuly (an URBN brand) is responsible for building and maintaining an AI-powered development harness that guides work from product definition through UX, design, and engineering implementation. The engineer will design agent instructions, schema contracts, quality gates, and feedback loops that keep AI-assisted workflows traceable and consistent across teams. It suits someone who wants to build the tooling and process infrastructure behind applied AI rather than simply use AI coding assistants.

Senior level · 5+ years · Full-time

Long application — this platform typically asks you to create an account and re-enter your work history.

Must have (4)
PythonLLMsJSON Schema or YamlGit
Nice to have (6)
LangChain, LangGraph, Crewai, Claude Agent Sdk or Google AdkGitHub Actions or Gitlab CiBashCursor, Claude Code or GeminiJira, Confluence or Monday.comMCP

“or” means any one of them counts — you don't need all of them.

We read this from the posting text with AI. Skim the description below before ruling yourself out.

How this req sits in the market our data

What won't set you apart
Python51%

Most people in this occupation already list these. Still required — just not what gets you shortlisted.

What the occupation pays Median $138,970 (middle half $107,524–$175,762).

Estimated from BLS employment for this occupation and area, per-skill prevalence across our listing corpus, and published wage benchmarks — as of Aug 7, 2026. It is a model, not a headcount.

Why we read it this way (9)

No work location is specified in the posting beyond the URBN/Nuuly brand context (Philadelphia-based company). The CBSA could not be determined from the text alone; the #LI-MW3 tag suggests a recruiter assignment but no city is stated.

No salary or compensation figures are provided.

The role's primary day-to-day work is building software tooling and agent infrastructure (APIs, workflow engines, automation), which maps most naturally to Software Developers (15-1252). The alt code 15-1299 is noted because the 'AI engineer / prompt/agent design' framing is an emerging occupation not perfectly captured by any single SOC.

Bash scripting appears in the responsibilities section alongside Python; it is listed as a supporting automation skill rather than a hard gate, so it is marked preferred.

LangChain/LangGraph, CrewAI, Claude Agent SDK, and Google ADK are all listed together as examples of agent development kits under qualifications; they are treated as interchangeable alternatives on a single preferred skill rather than separate hard gates.

Agentic coding platforms (Cursor, Claude Code, Gemini) are described as examples under 'familiarity with,' so they are marked preferred.

MCP (Model Context Protocol) and CLI-based tooling are mentioned under 'familiarity with tool-integration protocols' — marked preferred accordingly.

CI/CD pipeline experience (GitHub Actions, GitLab CI) appears in the qualifications list but is framed without firm gating language, so it is marked preferred.

Ignored 1 non-technology phrase(s) as skills (responsibilities/concepts, not named tools): AI agent design.

Read the full posting

The employer publishes the full description on their own site — read it there ↗. Or sign in to read it here — it's free, and it also lets you track this application.

Apply

Apply on employer site ↗