Data Scientist

Job DescriptionRole is onsite in Duluth, Georgia.\nNo third-parties will be considered.\n\nSenior Data Scientist (Machine Learning & MLOps)\nOur client is seeking a Data Scientist (Machine Learning & MLOps) to help build the next generation of its intelligent water utility platform. This is a highly hands-on role focused on designing, deploying, and operationalizing production machine learning solutions that process billions of IoT sensor readings each day.\nYou'll play a key role in establishing the organization's reusable machine learning framework, building scalable data pipelines, deploying models into production, and enabling future AI initiatives across the business. The ideal candidate combines deep data science expertise with strong machine learning engineering and MLOps experience, taking models from concept through production while building repeatable, automated workflows.\nThis is an opportunity to solve complex engineering and machine learning challenges while making a meaningful impact on water conservation, infrastructure management, and sustainability.\n\nKey Responsibilities\n\nDesign, build, deploy, and operationalize production-grade machine learning solutions using AWS services.\nDevelop scalable, repeatable machine learning pipelines supporting model training, validation, deployment, monitoring, and lifecycle management.\nBuild anomaly detection and predictive analytics models capable of supporting near real-time decision making.\nEngineer robust, production-scale data pipelines using AWS Glue, PySpark, SQL, and cloud-native technologies.\nProcess and analyze large-scale streaming IoT data.\nPerform feature engineering, model experimentation, evaluation, and performance optimization for production environments.\nDeploy machine learning models using AWS SageMaker and implement monitoring, retraining, automation, and governance throughout the ML lifecycle.\nCollaborate with Product Management and software engineering teams to translate business challenges into scalable machine learning solutions.\nDesign solutions that emphasize automation, repeatability, reliability, and operational excellence.\nParticipate in architecture discussions, code reviews, and Agile development activities.\nEvaluate emerging machine learning technologies and AWS capabilities to continuously improve platform performance and scalability.\n\n\nRequired Experience & Qualifications\n\n5+ years of experience designing and delivering production machine learning or advanced analytics solutions.\nDemonstrated success deploying machine learning models into production environments.\nStrong experience building scalable machine learning pipelines and production data workflows.\nHands-on experience with AWS SageMaker, AWS Glue, and related AWS analytics services.\nStrong production experience with PySpark and distributed data processing.\nExperience building or supporting MLOps practices, including model deployment, monitoring, automation, versioning, and lifecycle management.\nExperience processing large-scale datasets using distributed computing technologies.\nExperience supporting streaming or near real-time data processing environments.\nStrong Python programming skills utilizing modern machine learning libraries.\nAdvanced SQL proficiency.\nStrong understanding of feature engineering, model evaluation, experimentation, and production optimization.\nExperience collaborating closely with software engineers to integrate machine learning solutions into production applications.\nExcellent analytical, problem-solving, and communication skills with the ability to translate business problems into scalable technical solutions.\n\n\nPreferred Qualifications\n\nExperience with ClickHouse or other high-performance analytical databases.\nExperience building production solutions using streaming data technologies.\nExperience with anomaly detection, predictive maintenance, forecasting, or other advanced machine learning techniques.\nExperience working with large-scale IoT or time-series datasets.\nBackground in utilities, industrial IoT, manufacturing, or other data-intensive operational environments.\n\n\nWhat Will Make You Successful\nWe're looking for someone who enjoys solving complex engineering challenges—not simply building models in notebooks. The ideal candidate has experience taking machine learning solutions from concept through production, understands how to operationalize models at scale, and enjoys building reusable frameworks that enable future AI initiatives.\nSuccess in this role requires an engineering mindset, strong business curiosity, and the ability to build scalable, production-ready machine learning solutions that deliver measurable business value. Candidates whose experience is primarily centered on reporting, dashboards, or ad hoc analytics will likely not be the best fit.\n\nEducation\nBachelor's or Master's degree in Computer Science, Data Science, Statistics, Mathematics, Engineering, or another quantitative discipline, or an equivalent combination of education and practical experience.\n