Machine Learning Engineer

Our client is seeking a Machine Learning Engineer to lead the development, deployment, and ongoing optimization of production machine learning models and supporting MLOps pipelines. This role is ideal for an engineer who combines a strong foundation in machine learning, data science, and applied statistics with the systems expertise needed to transform complex, real-world data into reliable production capabilities. The ideal candidate will be comfortable owning the full ML lifecycle while collaborating closely with software, infrastructure, and technical program teams., * Own the end-to-end development and refinement of machine learning models, including supervised and unsupervised approaches for anomaly detection and operational monitoring.

• Analyze complex, multivariate datasets, perform data profiling and feature engineering, evaluate modeling approaches, and continuously improve model performance against operational requirements.
• Manage the complete MLOps lifecycle, including data ingestion, preprocessing, feature development, training, validation, deployment, model serving, and ongoing maintenance.
• Apply sound statistical and mathematical methods to model selection, validation, uncertainty assessment, and performance measurement.
• Develop and maintain scalable data preprocessing, enrichment, and feature pipelines that support current machine learning applications and future AI capabilities.
• Establish monitoring strategies for model performance, drift, anomaly detection effectiveness, data quality, and production output.
• Partner with software architecture and engineering teams to integrate machine learning models and outputs into broader applications and operational workflows.
• Maintain standards for data quality, freshness, lineage, governance, and interfaces between machine learning pipelines and downstream applications.
• Evaluate emerging machine learning technologies, foundation model approaches, and tooling to identify opportunities to enhance system capabilities.
• Optimize data structures, processing methods, and retrieval patterns to support efficient inference and timely delivery of model outputs.
• Produce clear technical documentation covering model architectures, assumptions, validation methods, pipeline designs, performance characteristics, and machine learning best practices.
• Collaborate with technical and business stakeholders to translate operational needs into effective machine learning solutions and communicate modeling decisions, risks, and trade-offs.

• Active Secret or TS/SCI security clearance.
• Bachelor’s degree or equivalent professional experience in Computer Science, Statistics, Applied Mathematics, Data Science, or another quantitative or technical discipline.
• Strong knowledge of machine learning, data science, applied statistics, and the mathematical principles underlying common modeling techniques.
• Hands-on experience building, deploying, and maintaining production machine learning pipelines spanning preprocessing, feature engineering, training, evaluation, and model serving.
• Proficiency with Python and machine learning frameworks or libraries such as scikit-learn, PyTorch, TensorFlow, or comparable technologies.
• Demonstrated experience working with complex, real-world datasets requiring substantial cleaning, transformation, analysis, and feature engineering.
• Ability to select appropriate statistical and machine learning methods, explain the reasoning behind technical decisions, and rigorously evaluate model performance.
• Strong written and verbal communication skills, including the ability to communicate technical concepts, modeling decisions, and trade-offs to both technical and non-technical audiences.

Preferred:

• Experience working with multivariate time-series data, anomaly detection, or machine learning applications operating in real-time or near-real-time environments.
• Familiarity with telemetry, aerospace, sensor, or other complex operational data environments.
• Experience deploying or supporting machine learning solutions within classified, air-gapped, restricted-access, or similarly controlled environments.
• Experience with AWS machine learning and data services, such as SageMaker and Step Functions, or comparable cloud technologies.
• Familiarity with MLOps platforms and tools such as MLflow, Kubeflow, or similar technologies.
• AWS Machine Learning, Data Engineering, or related technical certifications.
• Experience working in consulting, professional services, or other environments supporting multiple stakeholders or customers.