AI Quality Engineer

Unlock your potential with Dassault Systèmes, a global leader in Scientific Software Engineering, as we are hiring a AI Quality Engineer in Kuala Lumpur, Malaysia!

We are building a virtual companion for Operation Planning & Optimization applications that can reason, retrieve, and act autonomously. Powered by large language models (LLMs) and agentic workflows, the product will redefine how our customers interact with complex planning data. As an AI Engineer you will architect the intelligence, shape model behavior, and ensure safety and reliability at scale.

Role Responsibilities & Job Description:

• Prompt Engineering & Evaluation: Design and execute sophisticated test cases using prompt injection and adversarial testing to evaluate the AI’s boundaries and responses.
• LLM Benchmarking: Utilize advanced frameworks to measure performance in critical areas like hallucination rates, sentiment consistency, and context retention.
• Automated Validation: Build and maintain automated pipelines that leverage "LLM-as-a-judge" patterns to evaluate model outputs at scale.
• Safety & Bias Auditing: Lead "Red Teaming" sessions to identify potential biases, toxic content, or PII (Personally Identifiable Information) leaks.
• Regression Testing: Manage the evaluation of model performance across different versions to ensure seamless upgrades and stability.
• Collaboration & Delivery: Work with Product Owner, Developers, AI Engineers and UX Designers to deliver the Virtual Companion. Contribute to sprint planning, code reviews and documentation.
   

Requirements & Qualifications:

Technical Requirements:

• AI/ML Literacy: A strong grasp of LLM fundamentals, including tokens, temperature, top-p, and context windows.
• Programming: Proficiency in Python.
• API Testing: Expertise in testing RESTful APIs and WebSocket connections for real-time AI interactions.

Preferred Qualifications:

• Bachelor’s degree or above, with 3-5 years in software development and relevant experience specifically within the AI/ML testing landscape.
• Strong analytical and problem-solving skills
• Excellent people skills with collaborative attitude, team player
• Excellent communication skills and a good command of English
• A proactive mindset toward identifying "edge case" behaviors in generative models.