Sr Eng, Test

Role Overview: This role as a Senior Automation Engineer requires someone with 6+ years of strong hands-on experience in AI/ML model validation and testing. As part of the team, you will be focusing on ensuring the quality, reliability, accuracy, and robustness of AI/ML and LLM-based systems through systematic validation, data quality checks, and automated evaluation pipelines. Your work will play a crucial role in creating innovative solutions that contribute to saving and sustaining lives globally. Key Responsibilities: - AI / ML Model Validation - Design and execute validation strategies for AI/ML models, including supervised learning models and large language models (LLMs). - Perform functional, regression, and behavioral testing of ML models across versions. - Validate model outputs for accuracy, consistency, bias, and edge cases. - Evaluate LLM responses for correctness, relevance, hallucinations, and safety. - Data Quality, Drift & Monitoring - Design and implement data quality validation checks for training, validation, and inference datasets. - Detect and analyze data drift and concept drift across model iterations and production data. - Validate input data assumptions, feature distributions, and schema consistency. - Collaborate with data and ML engineers to identify and resolve data-related issues impacting model performance. - Python-Based Validation & Automation - Develop Python-based validation scripts and frameworks to automate model evaluation, data validation, and regression testing across model versions. - Implement automated checks for model performance metrics (precision, recall, F1, accuracy, etc.). - Build reusable validation utilities that integrate with ML workflows and pipelines. - LLM & Advanced AI Testing - Execute LLM evaluation workflows, including prompt-response validation, golden dataset comparisons, and regression testing across prompt or model changes. - Contribute to evaluation strategies for RAG (Retrieval-Augmented Generation) or multi-step LLM pipelines. - Support responsible AI initiatives by testing bias, robustness, and failure modes. - Collaboration & Quality Ownership - Work closely with ML engineers, data scientists, platforms, and product teams. - Actively participate in requirement discussions and model review sessions. - Clearly document test results, risks, and quality insights for stakeholders. - Contribute to the continuous improvement of AI testing practices and standards. Qualifications Required: - 4+ years of hands-on experience in AI/ML model testing, validation, or quality engineering. - Strong proficiency in Python for model validation and data analysis. - Experience validating supervised ML models and/or LLM-based systems. - Solid understanding of ML evaluation metrics and validation techniques. - Experience with data quality checks, drift detection, and dataset validation. - Familiarity with ML pipelines and model lifecycle (training, validation, inference). - Ability to analyze model behavior and explain quality risks clearly. - Good communication and collaboration skills. Company Details: At Baxter, the belief is that every person deserves a chance to live a healthy life. The company is redefining healthcare delivery to make a greater impact today, tomorrow, and beyond. Baxter colleagues are united by a Mission to Save and Sustain Lives, driven by a culture of courage, trust, and collaboration. Note: Equal employment opportunity and reasonable accommodations are provided by Baxter to individuals with disabilities. Role Overview: This role as a Senior Automation Engineer requires someone with 6+ years of strong hands-on experience in AI/ML model validation and testing. As part of the team, you will be focusing on ensuring the quality, reliability, accuracy, and robustness of AI/ML and LLM-based systems through systematic validation, data quality checks, and automated evaluation pipelines. Your work will play a crucial role in creating innovative solutions that contribute to saving and sustaining lives globally. Key Responsibilities: - AI / ML Model Validation - Design and execute validation strategies for AI/ML models, including supervised learning models and large language models (LLMs). - Perform functional, regression, and behavioral testing of ML models across versions. - Validate model outputs for accuracy, consistency, bias, and edge cases. - Evaluate LLM responses for correctness, relevance, hallucinations, and safety. - Data Quality, Drift & Monitoring - Design and implement data quality validation checks for training, validation, and inference datasets. - Detect and analyze data drift and concept drift across model iterations and production data. - Validate input data assumptions, feature distributions, and schema consistency. - Collaborate with data and ML engineers to identify and resolve data-related issues impacting model performance. - Python-Based Validation & Automation