Machine Learning Engineer Forecasting Production Systems

Mai Placement; Newark (NJ); On-site; USD 150,000 - 200,000; Full time

Job summary

Mai Placement in Newark, NJ is seeking a Machine Learning Engineer to own forecasting and production systems that drive sales projections, inventory planning, and purchasing decisions. You will deploy models in production and work with operations to ensure reliable, scalable forecasts.

This role emphasizes building end-to-end solutions, data pipelines, and measurable outcomes. Ideal candidates have proven experience deploying models, Python, time-series modeling, and delivering usable forecasts

Qualifications

• Proven experience deploying machine learning models into production.
• Strong Python and Scikit-learn experience.
• Strong statistical and predictive modeling foundation.
• Hands‑on experience with time series forecasting in real business settings.
• Experience working with large-scale / big data environments.
• Experience building data pipelines tied to ML systems.
• Ability to operate in fast‑paced, execution‑driven environments.

Responsibilities

• Own SKU-level forecasting models across sales, demand, and purchasing
• Deliver forecasts that directly influence inventory and operational decisions
• Deploy models into live environments used by operations and leadership
• Build and maintain data pipelines supporting real-time or near-term forecasts
• Translate operational problems into predictive models and deliver usable forecasts

Skills

Python

Scikit-learn

Time series

Production ML

Tools

SQL

Spark

Job description

Machine Learning Engineer – Forecasting & Production Systems
Newark, NJ
Salary: $120,000 – $180,000

Description / Position Overview

The business is operating without consistently reliable SKU-level forecasting, creating gaps in purchasing decisions, inventory planning, and revenue predictability.

This role exists to fix that.

You will own the development, deployment, and performance of forecasting systems that directly impact sales projections, demand planning, and purchasing decisions. This is not a research role. The expectation is clear: build models that work in production, improve accuracy over time, and drive measurable business outcomes.

Responsibilities

Forecasting Ownership

• Own SKU-level forecasting models across sales, demand, and purchasing
• Deliver forecasts that directly influence inventory and operational decisions
• Continuously improve model accuracy through iteration, testing, and feedback

Production Systems

• Deploy models into live environments used by operations and leadership
• Own model lifecycle: monitoring, retraining, performance tracking
• Ensure systems are stable, fast, and reliable under high-volume conditions

Data & Pipeline Ownership

• Build and maintain data pipelines supporting real-time or near-term forecasts
• Structure and clean large-scale transactional datasets
• Optimize data flow for speed, accuracy, and scalability

Business Execution

• Translate operational problems into predictive models
• Work directly with purchasing and operations teams to refine outputs
• Deliver usable forecasts — not theoretical models

Success Metrics (MANDATORY)

• Forecast accuracy improvement (MAPE, RMSE, or similar) over time
• Reduction in inventory overstock / stockouts
• Adoption of forecasts by purchasing and operations teams
• Model uptime and reliability in production environments
• Speed of iteration and deployment cycles

Requirements

• Proven experience deploying machine learning models into production
• Strong Python and experience with Scikit-learn or similar tools
• Strong statistical and predictive modeling foundation
• Hands‑on experience with time series forecasting in real business settings
• Experience working with large-scale / big data environments
• Experience building data pipelines tied to ML systems
• Ability to operate in fast‑paced, execution‑driven environments

Must-Haves

• Built forecasting models used for real business decisions
• Strong time series forecasting experience (sales, demand, SKU‑level preferred)
• Experience working with large datasets and high‑volume systems
• Ownership mindset — ability to deliver outcomes, not just models
• Proven ability to execute quickly and adapt under changing conditions

Compensation

$150,000-$200,000 per year