Back
Tier-1 brand and Bangalore metro increase applicant density despite niche senior AI automation skillset.
Specialized LLM agent and QA automation expertise is transferable across tech companies but less so outside technical domains.
Explicit 8+ years, mandatory Claude/OpenAI production experience, and strong TypeScript/Python make filters strict.
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-driven pipeline converting Jira tickets or product specs into first-draft Playwright tests using Claude.
Develop and maintain an autonomous agent to monitor test suites, detect flakiness, diagnose root causes, and propose or apply fixes with human review.
Own prompt engineering, evaluation metrics, acceptance workflows, and monitor operational KPIs like cost per test, acceptance rate, and flakiness reduction.
8+ years of production experience with TypeScript or Python, proficient in selecting appropriate language per task.
Production experience with Anthropic Claude API or OpenAI API, including multi-step agent patterns, tool use, and structured output handling.
Proven capability to rigorously evaluate LLM output quality and design resilient agentic systems with retries, fallbacks, and human escalation.
Ability to work with ambiguous and incomplete requirements to build novel AI automation solutions.
Experienced in designing autonomous AI agent systems integrated with software testing frameworks.
Comfortable collaborating with automation engineers to incorporate complex business logic into AI test generation.
Able to stay current and effectively evaluate fast-moving LLM tooling and cutting-edge AI techniques to improve test generation quality and efficiency.