AI Quality Engineer

Role: AI Quality Engineer
Location: This is a HYBRID position requiring 2 in-office days at local Deloitte office per week. Travel costs are not reimbursable.
Duration: 6+ Months

Only W2.

"We are seeking an AI Quality Engineer to join an innovative and high-impact team building AI capabilities within enterprise systems for a leading wealth management client. In this role, you will define, execute, and continuously improve quality engineering practices for AI-powered applications, including LLM-based assistants, retrieval solutions, and intelligent workflows. You will help ensure these solutions are reliable, accurate, secure, and fit for enterprise use by building robust testing strategies across model behavior, system integrations, user experience, and operational performance. This is an opportunity to shape the next generation of enterprise AI in a highly visible environment, where innovation, rigor, and business value all matter. The ideal candidate brings a quality-first mindset, strong testing discipline, and practical experience validating complex systems in regulated environments.

Key Responsibilities

Design and execute test strategies for AI applications, including functional, integration, regression, usability, and non-functional testing
Validate LLM-based solutions for accuracy, relevance, consistency, safety, latency, and task completion across realistic business scenarios
Create test cases, evaluation datasets, and quality benchmarks for prompts, retrieval pipelines, orchestration flows, and end-user interactions
Partner with AI engineers, product owners, and business stakeholders to define acceptance criteria and measurable quality standards
Identify model failure modes, edge cases, hallucination risks, and workflow breakdowns, and recommend corrective actions
Support automation of AI testing, monitoring, and quality reporting across development and production environments
Test data flows, APIs, integrations, and system dependencies that support AI-enabled business processes
Contribute to governance and release readiness by documenting defects, risks, test results, and quality decisions
Monitor production feedback, user behavior, and operational metrics to help drive continuous improvement
Help establish repeatable AI quality engineering practices, tooling, and controls for enterprise delivery

Required Qualifications

Bachelor's degree in Computer Science, Engineering, Information Systems, Data Science, or related field
6+ years of experience in quality engineering, software testing, QA automation, or related technical roles
Experience testing enterprise applications, APIs, data pipelines, or workflow-based systems
Experience evaluating AI or ML-based systems, including prompt behavior, output quality, or model-driven workflows
Strong understanding of test strategy, defect management, root cause analysis, and quality metrics
Familiarity with automation frameworks, test management tools, and CI/CD-aligned quality processes
Ability to work across technical and business teams to define and validate expected outcomes

Preferred Qualifications

Experience with LLM evaluation, prompt testing, RAG validation, or AI observability tools
Familiarity with Python, SQL, APIs, or scripting for test automation and data validation
Experience building synthetic datasets, golden test sets, or evaluation frameworks for AI use cases
Exposure to responsible AI, model risk, privacy, or governance controls in enterprise settings
Experience in financial services, wealth management, consulting, or other regulated environments

Core Competencies

Analytical rigor and attention to detail
Structured testing and defect analysis
Curiosity about model behavior and failure modes
Cross-functional collaboration
Clear communication of quality risks and trade-offs
Focus on reliability, user trust, and measurable outcomes"