Data Scientist

Optomi; New York (NY); Hybrid; USD 96,000 - 165,000; Full time

Job summary

Optomi is seeking a Senior Software Engineer with a strong background in machine learning, statistical modeling, and production model maintenance. This role focuses on maintaining, optimizing, and automating an existing forecasting model that supports business decisions across multiple markets.

The ideal candidate blends hands-on software engineering with solid statistical techniques, including time-series forecasting, regression, and anomaly detection.

Qualifications

• 5+ years of experience in machine learning engineering, data science, statistical modeling, or a related technical field.
• Strong hands-on programming experience with Python and SQL, including production data processing and model development.
• Experience with statistical analysis and machine learning techniques, particularly time-series forecasting, regression, and anomaly detection. Strong experience in at least two of these areas is preferred.
• Experience maintaining, optimizing, and troubleshooting existing production machine learning or statistical models.
• Knowledge of forecasting methodologies, predictive modeling, statistical validation, and model performance evaluation.
• Familiarity with data pipelines and orchestration technologies such as Airflow, dbt, or comparable tools.
• Experience working with cloud-based data platforms such as AWS, Snowflake, Databricks, or Apache Spark.
• Bachelor's degree in Computer Science, Mathematics, Statistics, Data Science, Engineering, or another quantitative discipline.

Responsibilities

• Own the ongoing maintenance, optimization, and reliability of an existing production forecasting model.
• Perform recurring monthly model updates, including data refreshes, performance validation, troubleshooting, and deployment.
• Evaluate forecasting accuracy and statistical performance, identifying opportunities to improve model outputs.
• Apply regression, anomaly detection, time-series analysis, and other statistical techniques to investigate model behavior and performance.
• Review, debug, refactor, and optimize existing Python and SQL code supporting production models.
• Implement automated workflows to improve model refresh processes, reliability, and operational efficiency.
• Monitor model performance, detect data drift or unexpected results, and investigate underlying issues.
• Partner with data engineering teams to troubleshoot upstream data quality problems and maintain reliable model inputs.
• Support the expansion and adaptation of existing models across additional international markets.
• Collaborate with technical and business stakeholders to ensure model outputs remain accurate, consistent, and actionable.
• Document model changes, validation results, operational processes, and ongoing improvements.

Skills

Python

SQL

Time-series forecasting

Anomaly detection

Model maintenance

Regression analysis

Education

Bachelor's degree in CS/Math/Stats/Data Science/Engineering

Tools

Airflow

dbt

AWS

Snowflake

Databricks

Apache Spark

Job description

• Hybrid 4 days a week in either NYC or Santa Monica, CA; 18 Month W2 Contract!


• We are seeking a Senior Software Engineer with a strong background in machine learning, statistical modeling, and production model maintenance. This role focuses on maintaining, optimizing, and automating an existing forecasting model that supports business decisions across multiple markets.


• The ideal candidate combines hands-on software engineering skills with a strong understanding of statistical techniques, particularly time-series forecasting, regression, and anomaly detection. This position requires someone comfortable working with existing model code, troubleshooting performance issues, validating model accuracy, and implementing recurring updates rather than primarily developing new models from scratch.

Requirements

• 5+ years of experience in machine learning engineering, data science, statistical modeling, or a related technical field.


• Strong hands-on programming experience with Python and SQL, including production data processing and model development.


• Experience with statistical analysis and machine learning techniques, particularly time-series forecasting, regression, and anomaly detection. Strong experience in at least two of these areas is preferred.


• Experience maintaining, optimizing, and troubleshooting existing production machine learning or statistical models.


• Knowledge of forecasting methodologies, predictive modeling, statistical validation, and model performance evaluation.


• Familiarity with data pipelines and orchestration technologies such as Airflow, dbt, or comparable tools.


• Experience working with cloud-based data platforms such as AWS, Snowflake, Databricks, or Apache Spark.


• Bachelor's degree in Computer Science, Mathematics, Statistics, Data Science, Engineering, or another quantitative discipline.

Nice to Have

• Experience with causal inference, experimental design, A/B testing, or advanced statistical modeling.


• Experience with MLOps, CI/CD pipelines, model versioning, and automated retraining.


• Master's degree in a quantitative or technical discipline.

Responsibilities

• Own the ongoing maintenance, optimization, and reliability of an existing production forecasting model.


• Perform recurring monthly model updates, including data refreshes, performance validation, troubleshooting, and deployment.


• Evaluate forecasting accuracy and statistical performance, identifying opportunities to improve model outputs.


• Apply regression, anomaly detection, time-series analysis, and other statistical techniques to investigate model behavior and performance.


• Review, debug, refactor, and optimize existing Python and SQL code supporting production models.


• Implement automated workflows to improve model refresh processes, reliability, and operational efficiency.


• Monitor model performance, detect data drift or unexpected results, and investigate underlying issues.


• Partner with data engineering teams to troubleshoot upstream data quality problems and maintain reliable model inputs.


• Support the expansion and adaptation of existing models across additional international markets.


• Collaborate with technical and business stakeholders to ensure model outputs remain accurate, consistent, and actionable.


• Document model changes, validation results, operational processes, and ongoing improvements.