AI QA Engineer

AI Engineer – London or Manchester office

About the Role

We are seeking a Full‑Stack Software Engineer with strong AI/ML expertise to design, build, and scale LLM‑enabled applications, including QA Agentic Frameworks and AI‑driven SDLC platforms. The role emphasizes building and validating production‑grade AI systems, ensuring the quality, reliability, robustness, and trustworthiness of LLM‑powered applications, agentic workflows, and ML pipelines.

What We Offer

• Opportunity to work on enterprise‑scale AI systems, including LLM‑driven and agentic workflows
• Ownership of AI‑specific quality strategy, tooling, and automation
• Close collaboration with Software Engineers, Product Owners, and AI Platform teams
• Exposure to agentic and AI‑driven testing frameworks
• A mandate to shape how AI quality is measured, validated, and governed across teams

Responsibilities

Full‑Stack Application Development

• Design, build, and maintain end‑to‑end applications—from front‑end UI to back‑end services
• Implement scalable APIs, microservices, and integrations supporting AI‑enabled workflows
• Drive architectural decisions and contribute to technical design reviews
• Build secure, intuitive user experiences that integrate smart, context‑aware AI components

AI/ML & LLM Integration

• Embed Large Language Models (LLMs) into applications, services, and workflows
• Implement and optimize agentic workflows, including planners, evaluators, and autonomous task agents
• Develop LLM‑powered features such as content generation, semantic search, test‑case generation, and intelligent orchestration
• Contribute to prompt engineering, output validation, RAG pipelines, and model behavior evaluation

Production‑Grade AI Systems Engineering

• Build reliable and observable AI systems with telemetry, monitoring, and fail‑safes
• Ensure robustness through structured validation, guardrails, and human‑in‑the‑loop controls
• Collaborate with QA and platform teams to ensure compliance, governance, and safe deployment of AI components

Quality, Testing, and SDLC Automation

• Integrate automated tests (unit, integration, regression, AI‑behavior checks) into CI/CD workflows
• Validate LLM responses, model performance, and agent reliability across changing datasets and prompts
• Partner with QA to enhance AI‑driven SDLC capabilities, including automated acceptance tests and intelligent issue detection

Collaboration & Cross‑Functional Partnership

• Partner closely with Product, Design, Data Engineering, and AI/ML teams
• Help shape best practices for AI‑enabled software development and contribute to internal engineering standards
• Provide guidance on feasibility, technical tradeoffs, and implementation strategy

Qualifications

• Bachelor’s degree in computer science, Software Engineering, Data Science, Artificial Intelligence, Machine Learning, or a related technical discipline OR equivalent practical experience in Quality Engineering for data‑driven or AI‑based systems
• 4+ years of experience in software engineering (full‑stack or backend‑focused)
• Strong proficiency in modern full‑stack development using frameworks such as React, Vue, or similar on the frontend and Node.js, Python, Java, or equivalent on the backend
• Experience building containerized, cloud‑native applications (AWS or Azure)
• Hands‑on experience integrating LLMs, generative AI APIs, or agent‑based systems
• Experience with agentic testing frameworks or autonomous test agents
• Hands‑on experience testing LLM‑based systems (chatbots, RAG, summarization, classification)
• Familiarity with AI governance, model risk management, or regulated environments
• Experience validating data pipelines and large‑scale datasets

Fitch Group is proud to be an Equal Opportunity and Affirmative Action Employer. We evaluate qualified applicants without regard to race, color, national origin, religion, sex, sexual orientation, gender identity, disability, protected veteran status, and other statuses protected by law.

#J-18808-Ljbffr…