Sr Software Development Engineer in Test - AI-First Development

🏢 Las Vegas Sands · all Las Vegas Sands jobs
📍 United States
📅 Posted 2026-08-19 · via Himalayas
🏷 Software-Development-Engineer-In-Test,Automation-Testing,QA-Engineering,AI-First-Development,Quality-Assurance-Engineering,Senior-Software-Development-Engineer-In-Test,Senior-Software-Development-Engineer-In-Test-(SDET),Senior-Test-Development-Engineer,AI-Testing-Engineer
Apply on original site ↗
Job Description: Position Overview The primary responsibility of the Senior Software Development Engineer in Test (AI-First Development) is to design, orchestrate, and validate the automated verification systems that gate every change shipped through the AI-First Software Development Lifecycle (SDLC). This role operates within an AI-First SDLC in which AI agents serve as primary producers of code, configuration, and test artifacts, while the Senior Software Development Engineer in Test (SDET) provides test strategy, context engineering, human-in-the-loop governance, and final accountability for the quality of delivered software. The Senior SDET is an experienced quality engineer or test automation engineer who has adopted modern AI-assisted development tools as a core part of their daily workflow and is prepared to grow into deeper agent orchestration, context engineering, and verification responsibilities. All duties are to be performed in accordance with departmental and Las Vegas Sands Corp.’s policies, practices, and procedures. All Las Vegas Sands Corp. Team Members are expected to conduct and carry themselves in a professional manner at all times. Team Members are required to observe the company’s standards, work requirements and rules of conduct. Essential Duties & Responsibilities - Test Strategy, Agent Workflow Design, and Orchestration - Design, build, and maintain AI agent workflows that produce unit, integration, end-to-end, performance, and security test suites from specifications and intent documents. - Decompose acceptance criteria and technical contracts into discrete, verifiable test scenarios that AI agents can execute effectively within defined boundaries. - Select and configure appropriate AI models, agent frameworks, and test-generation tooling for each workflow based on risk level, coverage requirements, and cost considerations. - Construct and maintain test context that provides agents with test patterns, fixture strategies, data classification rules, and domain information needed to produce correct and consistent test outputs. - Contribute to the testing toolchain, including reusable test skills, automation hooks, and project memory files that provide persistent context across agent sessions. Authoring of advanced toolchain components may be developed on the job. - Systematically capture defect patterns, escape modes, and verification failures from each development cycle and encode them back into shared context, test skills, and agent configurations so that subsequent work becomes more reliable. - Participate in collaborative refinement sessions to align on acceptance criteria, technical contracts, and test context packages before agent execution begins. - Verification and Quality Assurance - Operate the multi-layer Verification Framework on every pull request, with primary ownership of the automated testing layer, validating functional correctness, security posture, performance characteristics, code quality, and regulatory compliance. - Apply human oversight at governance checkpoints appropriate to the risk level of each workflow, including pre-execution review, in-flight observation, and post-execution audit. - Review, test, and approve AI-generated code and test suites, ensuring they meet Sands testing standards, architectural guidelines, and security requirements before promotion to production. - Verify that AI-generated tests exercise specified intent rather than mirroring implementation, and reject suites that pass without actually exercising the behavior the specification asked for. - Support independent QA verification after merge, contributing to system, integration, and regression testing in production-like environments and partnering with the QA Lead on User Acceptance Testing coordination where applicable. - Support agent observability practices that track test behavior, flakiness signals, coverage trends, and defect escape rates across workflows. -

← All remote jobs