Feelit is an Industry 4.0 company operating in the field of
Predictive Maintenance
, playing a key role in enabling sustainable and smart manufacturing. Our technology provides real-time alerts for upcoming failures, prevents unplanned downtime, and ensures optimal system availability through advanced data and AI-driven insights.
We are looking for a
passionate and highly motivated Data Scientist
who truly lives and breathes data, to join our
Data Science & Analytics team
and be part of a fast-growing and innovative environment.
In this role, you will research, design, implement, and evaluate advanced machine learning algorithms, working with large-scale pipelines and production-grade systems.
Our tech stack includes:
Python and its scientific ecosystem, Airflow, MLflow, InfluxDB, Redis, TimescaleDB, MySQL, and a broad Azure services stack.
Responsibilities
- Contribute to the development of cutting-edge predictive maintenance models using a variety of ML approaches
- Design and develop large-scale machine learning models
- Take full ownership of solutions, end-to-end — from EDA through model deployment to production
- Work closely with cross-functional teams including Product, Process, and R&D
Requirements
- M.Sc. in Computer Science, Computer Engineering, Statistics, or equivalent
- 3+ years of experience as a Data Scientist, developing in Python (and/or Spark) and working with time-series data
- Proven experience in Time Series and Signal Processing modeling
- Strong background in supervised and unsupervised learning
- Hands-on experience implementing ML algorithms and deploying production-grade applications
- Strong engineering mindset, with responsibility for both scientific and engineering aspects
- Experience working with Git (Bitbucket or GitHub)
Bonus Points
- Experience building cross-asset or system-level ML models
- Hands-on experience with Airflow and MLflow
- Experience with cloud computing (preferably Azure)
- SQL knowledge
- Familiarity with databases such as MySQL, Redis, and TimescaleDB (PostgreSQL)
