Back
Tier-1 employer and metro location increase competition, but senior niche LLM-agent skill reduces applicant density.
Highly domain-specific LLM-agent and test automation expertise limits cross-industry transferability.
Explicit 8+ years and mandatory Claude/OpenAI, agent design, and strong TypeScript/Python make filters stringent.
Login to See Your Match Score
Create a free account or log in to unlock your CV match score across:
Design and build an AI-powered test generation pipeline that converts product specs or Jira tickets into Playwright tests using Claude LLM.
Develop and maintain an autonomous agent to monitor test suites, detect flakiness, diagnose root causes, and propose or apply fixes with human-in-the-loop.
Own prompt engineering, evaluation metrics, and acceptance workflows to optimize test generation quality and maintenance efficiency.
8+ years of strong TypeScript or Python experience with ability to choose appropriate language for tasks.
Production experience with Anthropic Claude API or OpenAI API involving tool use, multi-step agent patterns, and structured output.
Proven capability to design agentic systems handling failures via retries, fallbacks, and human escalation.
Ability to rigorously evaluate LLM output quality and build systematic evaluation frameworks.
Experienced in creating novel AI-driven automation systems with high technical complexity in ambiguous or incomplete requirement environments.
Comfortable partnering with engineers and domain experts to tailor AI test generation to complex business logic.
Operates with a strategic focus on quality metrics, cost tracking, and iterative improvement of autonomous AI agents.