Bachelor's degree in Computer Science, Mathematics, Physics, Statistics, or Engineering.
Strong grasp of probability, statistics, and linear algebra; practical experience with Time-Series Analysis and Signal Processing.
Advanced knowledge of Python and the data science stack (Pandas, NumPy, Scikit-Learn, PyTorch/TensorFlow).
Experience writing production-grade software; comfortable with Object-Oriented Programming (OOP) and writing API endpoints.
Requirements:
Algorithm Development: Design and train models to solve specific physical problems (e.g., machine uptime detection or production count prediction).
Signal Processing: Apply statistical methods to raw time-series data to extract meaningful features and reduce noise.
Model Serving: Develop and maintain RESTful APIs (using frameworks like FastAPI) to expose your models for real-time inference.
Production Standards: Write clean, modular, and testable Python code. You are expected to use version control, write unit tests, and follow software design patterns.
Job description
Data Science at TRACTIAN
The Data Science team at TRACTIAN focuses on extracting valuable insights from vast amounts of industrial data. Using advanced statistical methods, algorithms, and data visualization techniques, this team transforms raw data into actionable intelligence that drives decision-making across engineering, product development, and operational strategies. The team constantly works on optimizing prediction models, identifying trends, and providing data-driven solutions that directly enhance the company’s operational efficiency and the quality of its products.
What you'll do
We are looking for a Machine Learning Engineer who focuses on the mathematical and algorithmic side of the product, but who is also capable of implementing their own solutions. You will be responsible for the full development cycle of a model: from statistical analysis and prototyping to writing the production code and APIs that integrate the model into our platform.
Responsibilities
Algorithm Development: Design and train models to solve specific physical problems (e.g., machine uptime detection or production count prediction).
Signal Processing: Apply statistical methods to raw time-series data to extract meaningful features and reduce noise.
Validation: Define and monitor metrics (accuracy, recall, precision) to validate model performance on real-world data before and after deployment.
Model Serving: Develop and maintain RESTful APIs (using frameworks like FastAPI) to expose your models for real-time inference.
Production Standards: Write clean, modular, and testable Python code. You are expected to use version control, write unit tests, and follow software design patterns.
Performance Optimization: Profile and optimize model inference code to ensure low latency and efficient resource usage.
Requirements
Education: Bachelor’s degree in Computer Science, Mathematics, Physics, Statistics, or Engineering.
Modeling Core: Strong grasp of probability, statistics, and linear algebra. Practical experience with Time-Series Analysis and Signal Processing.
Python Proficiency: Advanced knowledge of Python and the data science stack (Pandas, NumPy, Scikit-Learn, PyTorch/TensorFlow).
Software Engineering: Experience writing production-grade software. You must be comfortable with Object-Oriented Programming (OOP) and writing API endpoints.
Testing: Habitual use of testing frameworks (e.g., PyTest) to ensure algorithmic stability.
Data Handling: Proficiency with SQL for data querying and analysis.
Bonus Points
Experience with OEE (Overall Equipment Effectiveness) or industrial manufacturing data.
