Job Description

About us: 

Metro Global Solution Center (MGSC) is internal solution partner for METRO, a €29.8 Billion international wholesaler with operations in 32 countries through 625 stores & a team of 91,000 people globally. Metro operates in a further 10 countries with its Food Service Distribution (FSD) business and it is thus active in a total of 34 countries.

MGSC, location wise is present in Pune (India), Düsseldorf (Germany) and Szczecin (Poland). We provide HR, Finance, IT & Business operations support to 31 countries, speak 24+ languages and process over 18,000 transactions a day. We are setting tomorrow’s standards for customer focus, digital solutions, and sustainable business models. For over 10 years, we have been providing services and solutions from our two locations in Pune and Szczecin. This has allowed us to gain extensive experience in how we can best serve our internal customers with high quality and passion. We believe that we can add value, drive efficiency, and satisfy our customers.

Website: https://www.metro-gsc.in

Company Size: 600-650

Headquarters: Pune, Maharashtra, India

Type: Privately Held

Inception: 2011

We are seeking a highly skilled Test Automation Engineer to join the Agentic AI Squad within our AI Platform organization. The ideal candidate will have strong experience in designing, implementing, and maintaining automated test frameworks for complex distributed systems, with particular focus on AI/LLM-powered capabilities, agentic workflows, and high-scale backend services.

This role involves building robust automation pipelines, validating model-driven behaviors, ensuring system reliability through automated quality gates, and collaborating closely with AI Engineers and Architects to ensure end-to-end quality across the platform.

Key Responsibilities

Automation & Quality Engineering

• Design, implement, and maintain scalable automated test suites for API, integration, end-to-end, and workflow-level testing of agentic AI systems.
• Build automation frameworks that validate correctness, robustness, safety, and determinism in LLM-driven behaviors and multi-agent orchestration.
• Develop synthetic datasets, fixtures, and mocks to replicate complex agentic scenarios and edge cases.

AI/LLM-Specific Testing

• Implement automated evaluation pipelines for LLM outputs, including functional tests, regression checks, safety tests, and model-behavior verification.
• Collaborate with AI Engineers to integrate model evaluation metrics (e.g., hallucination detection, grounding accuracy, response consistency) into CI/CD systems.
• Validate prompt templates, agent tools, retrieval workflows, and chain-of-thought instrumentation.

Platform Integration

• Work with backend and platform teams to ensure test coverage across microservices, feature flags, workflow orchestrators, and event-driven systems.
• Contribute to testable system design and ensure new features include clear acceptance criteria and automation strategies.

CI/CD & Release Quality

• Integrate automated testing pipelines into GitHub Actions (or equivalent), ensuring fast feedback cycles and continuous verification.
• Implement quality gates, flakiness detection, and test result analytics to improve reliability and reduce manual QA overhead.
• Participate in release readiness reviews and ensure that automated checks provide full coverage for functional and non-functional requirements.

Bug Reproducing and Root Cause Analysis

• Understanding user feedback and reproducing bugs that have been submitted to the team
• Performing root cause analysis to enable AI Engineers to work on bug fixes and providing guidance on acceptance criteria

Qualifications

Must-Have Qualifications

Education

• Bachelor’s or Master’s degree in Computer Science, Software Engineering, or related technical field, or equivalent practical experience.

Work Experience & Skills

• 5+ years of experience in Test Automation Engineering, Software Development in Test (SDET), or similar roles.
• Profound experience working with a Cloud Platform (Google Cloud Platform preferred)
• Proven hands-on experience building automation frameworks at scale (Python or JavaScript/TypeScript preferred).
• Strong experience testing distributed systems, microservices, asynchronous workflows, and APIs.
• Familiarity with AI/LLM-based product testing, including prompt evaluation, workflow validation, or model-behavior testing.
• Strong experience with CI/CD (GitHub Actions preferred).
• Strong skills in debugging, root-cause analysis, and building reliable automation pipelines.
• Excellent communication skills in English (written and spoken).

Additional Information

Other Requirements

• Strong analytical mindset and ability to reason rigorously about system behavior.
• Ability to operate in a fast-paced environment with evolving AI technologies and requirements.
• Passion for automation, reproducibility, and engineering excellence.
• Collaborative approach and willingness to work closely with AI research and product teams.

Nice-to-Have

• Experience evaluating LLMs, agentic frameworks, or retrieval-augmented generation pipelines.
• Familiarity with synthetic data generation, dataset curation, or annotation workflows.
• Experience with Agile/Scrum methodologies.
• Understanding of safety frameworks, model confidence scoring, or risk-based testing in AI systems.