Objective & Engagement Parameters
The client is seeking an onshore contractor for an initial 6-month duration to integrate directly into the core engineering team. This position is strictly NOT FOR HIRE. The preferred location for this resource is Chicago, IL, operating on a hybrid schedule (2 days/week on-site).
The targeted candidate sits at a sweet spot of 7–10 years of experience. The client is explicitly not looking for a very senior or architect-level resource, but rather a highly capable, hands-on executor who can hit the ground running.
The Core Shift: Merging AI Development with QE Expertise to Empower the Community
Unlike standard full-stack development roles, this position requires an engineer who natively develops with AI tools and frameworks (e.g., LangChain, LangGraph, MCPs, and advanced RAG concepts) to accelerate delivery, while simultaneously building specialized tools to support and advance the Quality Engineering (QE) community.
The true value of this engineer lies in their dual capability: building AI-based applications through the lens of a QE expert. The successful candidate will focus heavily on:
- QE Tooling & Productivity: Designing and developing tools that enhance the QE community's day-to-day productivity.
- Standardization: Establishing unified standards for test cases, automation scripts, and technical capabilities across the QE ecosystem.
- EVALs Frameworks: Advancing robust EVALs frameworks to systematically test, validate, and ensure the AI platform consistently generates high-quality outputs.
Technical Domains of Mastery
The resource must demonstrate hands-on capability across three core pillars, complemented by a strong QA/QE pedigree:
- The MERN Stack & Full SDLC: Active, full-lifecycle application development using MongoDB, Express, React, and Node.js (or TypeScript/JavaScript variants), backed by 5+ years of deep familiarity with enterprise dev tools (Docker, Git, VS Code, npm/pip).
- Vertex AI & RAG Architecture: Demonstrated experience building AI capabilities, engineering agent behaviors, and defining pipelines specifically within the Google Cloud (GCP) Vertex AI ecosystem. Experience with equivalent AI services on other major cloud platforms (AWS, Azure) is an acceptable alternative.
- Core Backend & API Engineering: Robust knowledge of Python alongside a secondary familiarity with enterprise environments like Java to build highly integrated APIs, databases, and web services.
- QE Pedigree: Demonstrable experience in an active QE role with a deep, foundational understanding of modern QE concepts, automation practices, and testing methodologies is highly valued. Prior experience with automation tools like Playwright or Cypress.io is a plus.
- SDET skills - writing automation test scripts utilizing AI
Job Responsibilities
The true value of this engineer lies in their dual capability: building AI-based applications through the lens of a QE expert. The successful candidate will focus heavily on:
- QE Tooling & Productivity: Designing and developing tools that enhance the QE community's day-to-day productivity.
- Standardization: Establishing unified standards for test cases, automation scripts, and technical capabilities across the QE ecosystem.
- EVALs Frameworks: Advancing robust EVALs frameworks to systematically test, validate, and ensure the AI platform consistently generates high-quality outputs.