Data Scientist

This is a full-time employment contract for 12 months, with extensions. This would be reporting onsite in San Diego, CA Monday-Friday. Pay Range for this role is flexible $72-82/hr W2, based on years of experience and education.

Requirements/Experience:

• Must be willing to work in-person
• Build Machine Models and Algorithms - no just run a model
• Deploy a Machine Learning model
• Predictive Models
• Time-Series forecasting
• Python Programming
• Bachelors Degree

Highly Preferred:

Mathematics/Statistics/Physics Background

Masters or PH.D

JOB DESCRIPTION:

We are seeking a data scientist who is passionate about the physical world and wants to see their code come to life in the hum of machinery. You will be our go-to expert for translating high-frequency sensor data into predictive intelligence and for pioneering the use of Generative AI to solve core engineering challenges. You will collaborate shoulder-to-shoulder with mechanical, electrical, combustion and controls engineers to move beyond reactive problem-solving and create a proactive, data-driven manufacturing environment.

Responsibilities include:

• Build & Deploy Predictive Models: You will develop, train, and deploy machine learning models to predict equipment failures, forecast component lifespan, and identify sources of process instability. This includes everything from data ingestion and feature engineering to model validation and operational deployment.
• Pioneer Generative AI Applications: You will research, prototype, and implement Generative AI solutions to accelerate engineering workflows. This includes developing systems for intelligent document search across technical manuals, generating synthetic sensor data to augment our datasets, and creating AI-powered assistants to support root cause analysis.
• Master Our Sensor Data: Dive deep into complex, high-velocity datasets from our PLCs and data historians (OSIsoft PI). You will use advanced analytical techniques to clean, transform, and extract meaningful features from vibration, acoustic, temperature, and pressure sensor streams.
• Conduct Root Cause Analysis: When a process fails or quality dips, you will lead the analytical investigation. You’ll apply rigorous statistical methods to uncover the "why" behind the problem and present your findings to engineering teams.

Technical Toolkit:

• Core Programming: You are a master of Python and its scientific computing stack (pandas, numpy, scipy, scikit-learn). Your code is clean, efficient, and production-ready.
• Time-Series & ML: You have proven experience with time-series forecasting (e.g., ARIMA, Prophet) and advanced machine learning models (e.g., LSTMs, Gradient Boosting, Isolation Forests). Experience with a major framework like TensorFlow or PyTorch is essential.
• Data Systems: You are fluent in SQL and have hands-on experience with industrial time-series databases and historians like OSIsoft PI, InfluxDB, or similar platforms.
• Cloud & MLOps: You are comfortable working in a cloud environment (AWS preferred) and have experience with MLOps principles—versioning data and models, deploying endpoints, and monitoring performance.