Lead AI Engineer
Core
Design and develop autonomous and multi-agent workflows for end-to-end software test automation, including test generation, code creation, validation, debugging, failure triage, and self-healing.
Role type
Lead AI Engineer (Test Automation)
Builds
AI agents for software testing and validation pipelines
Domain
Software Engineering / AI / Test Automation
Deliverable
production ML models | product features
Required skills
LLM integration, prompt engineering, RAG, AI-agent development, Python, TypeScript, API design, agent orchestration frameworks, AI evaluation, observability, vector databases, embeddings, CI/CD pipelines
Preferred skills
Playwright, Angular, React, MCP servers, Jenkins, LLM cost optimization, caching, model routing
Technologies
LangGraph, OpenAI Agents SDK, CrewAI, AutoGen, Semantic Kernel, LangSmith, Langfuse, Arize Phoenix, Jenkins, GitHub
Responsibilities
Design and develop autonomous and multi-agent workflows for end-to-end software test automation; Build AI agents for test generation, code creation, validation, debugging, failure triage, and self-healing; Maintain application knowledge bases using embeddings, retrieval, and context strategies; Define agent instructions, guardrails, validation checkpoints, and human-in-the-loop review processes; Establish evaluation practices using golden datasets, regression evaluations, LLM-as-judge methods, and reliability metrics; Instrument and monitor agents for accuracy, reliability, latency, token cost, and maintainability in production; Integrate agents with UI, API, database, end-to-end testing, GitHub, Jenkins, and other engineering workflows; Set technical standards and best practices for agentic development and AI-assisted testing; Mentor engineers, run design reviews, and raise the team's AI engineering maturity
Seniority
Senior, hands-on IC with leadership responsibilities
