Lead Machine Learning Engineer
hace 19 horas
Pittsburgh
Job Title: Machine Learning Lead Engineer Work Location: Pittsburgh, PA Duration: 6 month Contract-to-Hire Education/Experience Required: Leading ML/DS projects in an industrial setting, experience working with time-series data and SCADA applications. Job Description & Responsibilities : • Lead end-to-end delivery of data engineering and machine learning projects that improve operational efficiency and reduce emissions in natural gas development, production, and midstream operations., • Own the full lifecycle of ML solutions from ideation and scoping, to data discovery, modeling, validation, deployment, and long-term monitoring., • Provide technical leadership for a small but high-impact Data Engineering & Machine Learning team, including mentoring, code reviews, and setting best practices for quality and reliability., • Work on-site with engineering, operations, and SCADA teams on-site to understand real-world constraints, define use cases, and translate business problems into data-driven solutions., • Lead the effort to productionize existing models and scale multiple proof-of-concept solutions into robust, maintainable, and observable production systems., • Architect, design, and implement data pipelines that ingest, clean, transform, and store large volumes of time-series and event data from SCADA systems, field sensors, and other industrial data sources., • Develop and refine machine learning models focused on time-series problems such as forecasting, anomaly detection, remaining useful life estimation, and performance optimization of assets., • Contribute to and help lead Digital Twin Analytics initiatives, integrating physics-based and data-driven models to simulate and optimize complex systems in the field., • Collaborate on the design and implementation of anomaly detection frameworks that surface early warning signals for equipment failure, process instability, and emissions events., • Partner with software and DevOps engineering to design and implement MLOps practices, including CI/CD for ML, feature stores, model versioning, model performance tracking, and automated retraining pipelines., • Establish standards for model validation, A/B testing, and offline/online evaluation to ensure robustness and reliability in operational environments., • Communicate technical concepts, tradeoffs, and results clearly to both technical stakeholders and non-technical operations leaders, including presenting insights and recommendations to leadership., • Evaluate new tools, libraries, and cloud-native services in the data and ML ecosystem and make recommendations to improve performance, scalability, and developer productivity., • Champion a culture of experimentation, data quality, and continuous improvement while keeping a strong focus on safety, regulatory compliance, and environmental impact. Skills & Qualifications : • Bachelor's degree in Computer Science, Data Science, Engineering, Applied Mathematics, or a related field; a graduate degree is preferred but not required with sufficient experience., • 7+ years of hands-on experience in Data Science, Machine Learning, or Data Engineering, with at least 2+ years in a lead or senior role driving projects from concept to production., • Strong proficiency in Python for data engineering and machine learning, including experience with common data and ML libraries (for example pandas, NumPy, scikit-learn, PyTorch or TensorFlow, statsmodels)., • Strong SQL skills and experience working with relational databases, time-series databases, or data warehouses for large-scale analytics., • Proven experience working with time-series data in industrial or operational settings, including feature engineering, resampling, handling missing data, and building time-series forecasting or anomaly detection models., • Experience integrating and analyzing SCADA data or similar industrial control and telemetry systems in energy, utilities, manufacturing, or related heavy industry., • Solid understanding of data engineering concepts including ETL/ELT pipelines, batch and streaming architectures, and data modeling for analytical workloads., • Hands-on experience with cloud platforms (such as AWS, Azure, or GCP) and modern data tooling, for example cloud storage, managed databases, containerization, and workflow orchestration tools., • Practical exposure to MLOps practices, including deployment of models to production, monitoring model performance in real time, and maintaining models over their lifecycle., • Familiarity with concepts and techniques related to Digital Twin Analytics, physics-informed models, or asset performance management in an industrial context is a strong plus., • Strong software engineering fundamentals including version control (Git), code review practices, testing, and documentation., • Demonstrated ability to lead cross-functional initiatives, prioritize a portfolio of projects, and manage stakeholder expectations in a fast-moving environment., • Excellent communication skills, with the ability to explain complex technical concepts clearly and to influence decision making among operations leaders, field engineers, and executives., • Willingness to work on-site in the Pittsburgh, PA area and periodically visit field or plant locations as needed; relocation support is available for exceptional candidates.