Lead Software Engineer in Test – Agentic AI (Remote - US)
Core
Lead a horizontal Software Engineer in Test (SET) team to build AI-driven testing agents, shared test infrastructure, and governance for Agentic AI systems.
Role type
Senior IC Lead Software Engineer in Test (Agentic AI)
Builds
AI-driven test automation frameworks, regression suites, and shared testing infrastructure for engineering teams.
Domain
Healthcare technology + Agentic AI / LLM systems
Deliverable
production ML models
Required skills
Automation framework design (JavaScript/TypeScript, Java), AI agent testing (LLM workflows, RAG, autonomous agents), API/backend/UI testing, CI/CD integration, Cloud-native environments (Azure/AWS/GCP, Docker, Kubernetes), Distributed system validation, Test strategy & execution, Mentorship
Preferred skills
AI observability, Telemetry, Vector databases, Prompt evaluation frameworks, Event-driven architectures, Healthcare compliance (HIPAA)
Technologies
Playwright, Cypress, Postman, K6, LangGraph, CrewAI, AutoGen, Semantic Kernel, Azure DevOps, GitHub Actions, SQL Server
Responsibilities
Design and maintain scalable automation frameworks across UI, API, backend, and AI-driven applications; Lead quality engineering for Agentic AI systems including LLM workflows and autonomous agents; Validate complex AI agent behaviors like multi-agent coordination and prompt chaining; Develop functional, integration, and performance testing strategies for cloud-native environments; Mentor QA engineers and drive best practices for code quality and testability.
Seniority
Senior, hands-on IC with leadership responsibilities