Lead Software Engineer in Test
Core
Lead quality engineering strategy and execution for next-generation AI-powered applications, designing scalable automation frameworks and validating complex AI agent behaviors.
Role type
Lead Software Engineer in Test (Agentic AI)
Builds
Scalable automation frameworks, regression test suites, and validation pipelines for UI, API, backend, and AI orchestration layers.
Domain
Healthcare technology + Agentic AI / LLM systems
Deliverable
production ML models | product features
Required skills
Designing scalable automation frameworks, validating AI agent behaviors (multi-agent coordination, tool calling, prompt chaining), functional/integration/regression/E2E testing, CI/CD integration, cloud-native environment management, API/backend/UI testing, mentoring QA engineers, understanding of automation architecture and design patterns.
Preferred skills
AI observability, telemetry, RAG pipeline validation, vector databases, prompt evaluation frameworks, event-driven architectures, healthcare systems/HIPAA compliance knowledge.
Technologies
Playwright, Cypress, Postman, K6, LangGraph, CrewAI, AutoGen, Semantic Kernel, Azure, AWS, GCP, Docker, Kubernetes, SQL Server, Azure DevOps, GitHub Actions.
Responsibilities
Design and maintain scalable automation frameworks and regression test suites across distributed systems. Lead quality engineering initiatives for Agentic AI systems including LLM workflows and autonomous agents. Validate complex AI agent behaviors such as multi-agent coordination and conversational workflows. Develop and execute testing strategies across cloud-native environments. Collaborate with engineering and product teams to integrate testing throughout the SDLC. Mentor QA engineers and contribute to scalable QA standards and continuous improvement initiatives.
Seniority
Senior, hands-on IC with leadership responsibilities
