Software Engineer In Test

Job Description

Job Title: Software Development Engineer in Test (SDET) – Conversational AI

Location: Hartford, CT or Wellesley, MA (100% Onsite)

Duration: 12-Month Contract (Potential Extension)

Work Authorization: Green Card or U.S. Citizen

Experience: 10+ Years Preferred

Position Overview

We are seeking a Senior Software Development Engineer in Test (SDET) to design and build robust test infrastructure for a high-volume Conversational AI platform. This is a developer-centric quality engineering role focused on building reusable test harnesses, automation frameworks, and AI evaluation systems—not traditional manual QA. You will empower engineering teams to own quality across voice, chat, and LLM-driven workflows.

Key Responsibilities

• Framework & Infrastructure: Architect, build, and maintain reusable test frameworks and harnesses for Java/Node.Js backend services, REST APIs, and frontends.
• Conversational AI & LLM Testing: Design test strategies for multi-turn conversations, intent recognition, context handling, and orchestration logic. Apply modern evaluation methods like LLM-as-a-Judge.
• Developer Enablement: Provide testing patterns, documentation, and tools that allow developers to write automated tests seamlessly and own product quality.
• Automation & Execution: Automate Voice and Chat channels using modern tooling, integrate tests into GitHub Actions CI/CD pipelines, and establish test data strategies.
• Quality Advocacy: Partner with Architecture, Engineering, and Product teams to eliminate testing gaps, mentor engineers, and promote Test-Driven Development (TDD).

Required Qualifications

• Core Experience: 5+ years in software engineering with 3+ years specifically focused on SDET, framework design, and test infrastructure.
• Development Skills: Strong hands-on programming experience in Java or Node.Js/JavaScript, alongside deep knowledge of Object-Oriented Design.
• API & UI Testing: Advanced skills in REST API automation, contract testing, and tools like Playwright, Selenium, Jest, JUnit, Postman, Bruno, or Cucumber.
• Conversational AI / Voice / Chat: Hands-on experience automating tests for chatbots, voice bots, NLP systems, context/intent recognition, or AI agents.
• AI Evaluation: Exposure to AI/LLM testing methodologies (e.G., response accuracy validation, LLM-as-a-Judge).
• CI/CD & Onsite Availability: Experience integrating test suites into CI/CD (GitHub Actions) and ability to work fully onsite in Hartford, CT or Wellesley, MA.

Preferred Qualifications

• Experience with specialized voice/chat testing tools like Cyara or Hammer.
• Proven track record designing enterprise-wide test infrastructure used by multiple teams.
• Hands-on experience testing autonomous AI agents, agentic workflows, or cloud-native architectures.
• Background in performance, load, and scalability testing.

Chandan Singh

+1 201-499-7364

chandan.s@globalapplications.com