AI Testing & Automation Engineer — Performance & QA

Wipro; Bellevue (WA); On-site; USD 100,000 - 180,000; Full time

Benefits offered by this job

Medical and dental benefits options

Disability insurance

Paid time off

Job summary

Wipro is seeking an AI testing engineer to design and build end-to-end testing frameworks and CI/CD pipelines for model validation.Responsibilities include performance testing under high concurrency and maintaining automated suites to verify agent behavior and API contracts after each release.

The role emphasizes building LLM evaluation pipelines for relevance, groundedness, and hallucination metrics, integrated into the CI/CD workflow, ensuring quality gates before deployments.

Qualifications

• Mandatory Skills: Enterprise Platform Engineering Python.
• Experience: 8-10 Years
• The compensation ranges from $100,000 to $180,000.

Responsibilities

• Design and build end-to-end AI testing frameworks covering unit, functional, integration, and regression testing including automated test case generation and model output validation against defined quality benchmarks.
• Develop load and performance testing simulating high-concurrency scenarios to validate scalability, latency SLAs, and platform stability under peak load.
• Build LLM evaluation pipelines covering relevance, groundedness, and hallucination metrics integrated into CI/CD workflows to enforce automated quality gates before every model or agent deployment.
• Own regression testing strategy across the AI platform maintaining automated suites that validate agent behavior, RAG pipeline accuracy, and API contracts after every release to prevent quality degradation.

Skills

Enterprise Platform Engineering

Python

Job description

Wipro is seeking an AI testing engineer to design and build end-to-end testing frameworks and CI/CD pipelines for model validation.Responsibilities include performance testing under high concurrency and maintaining automated suites to verify agent behavior and API contracts after each release.

The role emphasizes building LLM evaluation pipelines for relevance, groundedness, and hallucination metrics, integrated into the CI/CD workflow, ensuring quality gates before deployments.