AI / ML QA Engineer

Contract Duration: May 4, 2026 to November 4, 2026

Overview

We are seeking an experienced AI / ML QA Engineer to support testing and validation of advanced machine learning and generative AI systems. This role focuses on ensuring model quality, reliability, and responsible AI practices across a range of applications including NLP, classification, recommendation systems, and large language models.

Key Responsibilities

Functional and Model Testing

• Design and execute test cases for AI and ML models including NLP, classification, recommendation, and generative AI systems
• Validate outputs for accuracy, consistency, and expected behavior across diverse datasets and inputs
• Perform regression testing following model updates, retraining cycles, or data changes

Prompt and LLM Testing

• Develop and maintain prompt test libraries for LLM based features
• Evaluate responses for relevance, tone, factual accuracy, and alignment with business rules
• Identify hallucinations, response drift, and edge case failures

AI Safety and Red Teaming

• Conduct adversarial testing to uncover vulnerabilities such as prompt injection and jailbreak scenarios
• Assess outputs for bias, fairness, and compliance with responsible AI standards
• Document risks and collaborate with model teams on remediation strategies

Test Automation and Tooling

• Build and maintain automated test suites using Python based frameworks
• Track and report quality metrics, model performance benchmarks, and defect trends

Collaboration and Documentation

• Work closely with data scientists, ML engineers, and product teams
• Develop clear test plans, defect reports, and evaluation summaries
• Contribute to QA standards and best practices for AI systems

Required Skills

• Hands on experience testing AI and ML models including NLP, classification, and generative AI
• Strong experience with LLM testing including prompt engineering and evaluation of hallucinations, bias, and response quality
• Proficiency in Python and test automation frameworks
• Experience working with CI CD pipelines
• Solid understanding of regression testing

Nice to Have

• Experience in banking or financial services
• Exposure to AI safety and red teaming techniques such as prompt injection and jailbreak testing
• Knowledge of responsible AI and model governance principles
• Familiarity with LLM evaluation tools and frameworks
• Experience testing recommendation or ranking systems
• Exposure to ML pipelines and MLOps workflows
• Understanding of bias and fairness metrics

Note: We use AI tools to: obtain basic information, detect plagiarism, false employment history or references, categorize your skills, and do an initial match with job posting.