Data Scientist

Assess, interrogate, and improve existing machine learning models that are currently underperforming. Identify opportunities to enhance model accuracy, performance, and business value. Train, tune, and optimize machine learning models, including addressing overfitting, underfitting, and other performance issues. Develop and refine imputation models to address missing metadata and feature gaps within the data. Analyze data quality challenges and determine the impact of missing information on model performance. Evaluate whether pursuing additional data collection efforts is worthwhile from both a cost and modeling perspective. Determine appropriate sample sizes and data requirements to ensure modeling efforts are neither over- nor under-scoped. Partner with Data Engineers while maintaining sufficient data pipeline knowledge to review and validate pipeline logic and implementation. Contribute to the overall production machine learning ecosystem, including model maintenance, versioning, and operational best practices. Help the team meet near-term delivery deadlines where current modeling resources have not met expectations. Communicate findings, recommendations, and tradeoffs effectively to both technical and non-technical stakeholders. Technical Environment Production environment is hosted in AWS. Dedicated Data Engineering resources are responsible for building production pipelines. Dedicated MLOps resources are available, although familiarity with MLOps concepts would be beneficial. Models are already operating in production and require ongoing enhancement and optimization. Ideal Candidate Profile Strong machine learning practitioner with a focus on modeling rather than platform engineering. Deep understanding of classical machine learning techniques, including regression modeling. Experienced in diagnosing and improving model performance. Strong analytical mindset with the ability to assess data quality and feature availability challenges. Pragmatic problem solver capable of balancing model improvement against business effort and cost. Effective communicator who can clearly explain technical decisions and recommendations. Familiarity with production-grade machine learning systems and operational considerations. Must-Have Skills: Machine Learning model development and optimization Classical machine learning algorithms Regression modeling Model training, evaluation, and performance tuning Experience addressing overfitting and underfitting Feature engineering and missing data/imputation techniques Strong statistical analysis and sampling methodology knowledge Data quality assessment and root-cause analysis Python-based machine learning development Experience with production machine learning systems Model versioning and lifecycle management Ability to review and understand data pipeline code Strong communication and stakeholder engagement skills Pragmatic, business-focused problem-solving approach Nice-to-Have Skills: AWS experience MLOps concepts and tooling Model deployment and monitoring experience CI/CD for machine learning Energy, oil