Software Engineer III

Electronic Arts creează experiențe de divertisment de următorul nivel, care inspiră jucătorii și fanii din întreaga lume. Aici, toată lumea face parte din poveste. Face parte dintr-o comunitate care stabilește legături în întreaga lume. Un loc în care creativitatea prosperă, sunt încurajate noi perspective, iar ideile sunt importante. O echipă în care toată lumea face jocul posibil.

In FC Quality Verification Engineering, our mission is to help our teams identify quality issues earlier. We build automation frameworks and developer tools that combine software development and applied AI/ML to improve how we test EA-SPORTS FC.

You will work with us to build automated testing frameworks and evaluation tools, applying AI and machine learning to expand our test coverage. You will report to our Engineering Manager. You will work hybrid, at least 3 days a week, from our office in Burnaby, BC.

Responsibilities:

• Build automated testing frameworks, validation checks, and CI/CD pipeline integrations with reproducible diagnostics.
• Develop methods that help us explore complex software behaviour, identify coverage gaps, and detect defects.
• Build automated checks to validate software behaviour and data against requirements.
• Develop evaluation frameworks for generative AI and LLMs-based systems (e.g., implementing LLMs-as-a-judge patterns, rubric-based scoring, and automated calibration) alongside deterministic validation checks.
• Apply generative AI, NLP, and machine learning, balancing heuristic, deterministic, and model-based approaches to solve complex software testing problems.
• Integrate testing tools into development pipelines, producing reproducible diagnostics, and support the software you deliver.
• Prototype latest machine learning and LLMs capabilities, and collaborate with engineering, design, and quality partners to clarify requirements, review code, and resolve blockers.

Required qualifications:

• 5+ years of professional software engineering experience, including 2+ years of hands-on experience building, integrating, or evaluating AI/ML and LLMs-based systems.
• A Master of Science in Computer Science, Mathematics or a related field, or equivalent professional engineering experience.
• In-depth experience with LLMs, generative AI, and NLP concepts, architectures, and failure modes.
• Experience developing evaluation frameworks for generative systems, including dataset curation, model-as-a-judge design, validation criteria, error analysis, and quantitative/qualitative metrics.
• Proficiency in Python, algorithms, data structures, modular design, automated testing, debugging, and version control.
• Experience preparing datasets, defining validation criteria, and performing error analysis using quantitative ML metrics.
• Experience with natural language processing or large language models, such as prompting, fine-tuning, or retrieval-augmented generation.