Lead Data Scientist

InnoCore Solutions, Inc.; United States; On-site; USD 180,000 - 260,000; Full time

Job summary

InnoCore Solutions, Inc. seeks a Lead Data Scientist to architect and deploy ML-powered demand forecasting in automotive logistics. You will drive LP/MILP/DP optimization, build scalable Python solutions with Pyomo, PuLP, OR-Tools, and deploy on AWS.

Role requires 2+ years ML in real problems, strong forecasting and time-series skills, and experience with SageMaker, CodePipeline, and CI/CD for ML. Collaboration with supply chain teams is essential.

Qualifications

• Advanced degree (MS or PhD) in Statistics, CS/DS, OR, Industrial Engineering or Applied Mathematics.
• 2+ years applying ML techniques to real-world problems.
• Strong forecasting, time series and statistical modeling background.

Responsibilities

• Develop optimization models (LP, MILP, DP) for complex supply chain problems.
• Build scalable optimization solutions using Python and optimization libraries and deploy them on cloud platforms.
• Translate business requirements into mathematical models and decision-support tools.
• Monitor model accuracy, drift, and forecasts using business inputs.
• Align modeling with KPIs like fill rate, inventory turnover, and lead time.
• Develop ML pipelines with SageMaker, Step Functions, and CodePipeline.
• Automate training, testing, deployment, monitoring, and rollback for ML systems.
• Implement SageMaker Model Monitor, Clarify, and CloudWatch for performance and bias monitoring.
• Use Lambda and EventBridge for real-time retraining triggers.
• Define and manage SageMaker Feature Store for training and inference consistency.
• Create AI-driven decision support tools including classification, clustering and explainable AI.
• Explore Generative AI for scenario simulation and automated reporting.
• Collaborate with business teams to embed AI into dashboards, alerts, or APIs.
• Bridge between technical teams and business stakeholders in supply chain/logistics planning.

Skills

Optimization models

Python

Forecasting

Time series

MLOps

CI/CD

SQL

GitHub

Education

MS or PhD in quantitative field

Tools

Pyomo

PuLP

Google OR-Tools

Gurobi

IBM CPLEX

Job description

We are hiring a Lead Data Scientist to drive the architecture, development, and deployment of machine learning and AI-powered demand forecasting solutions within the automotive logistics ecosystem. This role is central to improving vehicle and parts supply chain visibility, inventory accuracy, and fulfillment predictability using Linear Programming (LP), Dynamic Programming (DP), machine learning, MLOps best practices, and AWS-native services.

Responsibilities:

• Develop and implement optimization models using Linear Programming (LP), Mixed Integer Linear Programming (MILP), and Dynamic Programming (DP) to solve complex supply chain problems, including inventory optimization, production planning, transportation, and network optimization.
• Build scalable optimization solutions using Python and optimization libraries such as Pyomo, PuLP, OR-Tools, Gurobi, or CPLEX, and deploy them on cloud platforms.
• Collaborate with supply chain, operations, and business stakeholders to translate complex business requirements into mathematical optimization models and decision-support solutions.
• Continuously monitor model accuracy and improve forecasts based on error analysis, drift detection, and business input.
• Align modeling strategy with supply chain KPIs such as fill rate, inventory turnover, order-to-ship lead time, and forecast bias.
• Develop and manage end-to-end ML pipelines using Amazon SageMaker Pipelines, AWS Step Functions, and CodePipeline.
• Automate model training, testing, deployment, monitoring, and rollback using CI/CD practices tailored for ML.
• Implement SageMaker Model Monitor, SageMaker Clarify, and CloudWatch for continuous model performance, bias, and drift monitoring.
• Use AWS Lambda and EventBridge to integrate real-time triggers for retraining or alerts.
• Define and operate a SageMaker Feature Store for training and inference consistency.
• Develop AI-driven decision support tools using classification models, clustering, anomaly detection, and explainable AI (XAI).
• Explore use of Generative AI for scenario simulation, forecast explanation, and automated reporting.
• Collaborate with business teams to embed AI recommendations into dashboards, alerts, or APIs.
• Act as a bridge between technical teams and business stakeholders (supply chain, logistics, planning).
• Promote best practices in model documentation, reproducibility, testing, and governance.

Requirements:

• Experience developing optimization models using Linear Programming (LP), Mixed Integer Linear Programming (MILP), Dynamic Programming (DP), or other Operations Research techniques.
• Proficiency in Python and experience with optimization frameworks such as Pyomo, PuLP, Google OR-Tools, Gurobi, or IBM CPLEX.
• At least 2 years of experience in applying statistical and machine learning techniques to real-world problems.
• Solid understanding of forecasting techniques, statistical modeling, and time series analysis.
• Knowledge of methods like Logistic Regression, Time Series Analysis, GLMs, Mixed Modeling, Multivariate Statistics, Predictive Modeling, Decision Trees, Gradient-Boosted Trees, Random Forests, and Neural Networks.
• Hands-on experience with AWS services: Amazon SageMaker, S3, Glue, Lambda, CloudWatch, Step Functions, ECR, CodePipeline.
• Strong SQL skills and familiarity with data lakes, Redshift/Snowflake, and distributed data processing (Spark).
• Experience implementing MLOps pipelines in production environments.
• Deep understanding of automotive logistics, including order lifecycle, dealer distribution, parts inventory, and transportation flows.
• Experience with version control systems such as GitHub, and familiarity with CI/CD practices to streamline model deployment and code management.
• Prior experience with demand forecasting or supply chain analytics at scale.

Education:

• Advanced degree (MS or PhD) in a quantitative field including but not limited to Statistics, Computer Science/Data Science, Operations Research, Industrial Engineering, or Applied Mathematics.