The project leverages large datasets on vehicles and dealership service transactions to develop predictive and prescriptive tools that help car dealers make better business decisions.
responsibilities :
Design, build, and maintain end-to-end ML pipelines - from data ingestion and feature engineering to model training, deployment, and monitoring in production.
Manage the full lifecycle of ML models, including deployment on AWS, retraining automation, versioning, and A/B testing to ensure optimal performance.
Develop and maintain CI/CD pipelines for ML, integrating automated testing, containerization, and continuous delivery to streamline deployments.
Implement monitoring and observability frameworks for deployed models - track data drift, performance, and errors; build dashboards and alerts to ensure reliability.
Collaborate closely with data scientists, data engineers, and product teams to transform prototypes into scalable production solutions, incorporating domain expertise to improve accuracy and business impact.
Continuously monitor and improve models in production, retraining on new data, optimizing infrastructure, and enhancing system scalability, efficiency, and security.
requirements-expected :
Minimum 2 years of experience building, deploying, and maintaining machine learning models or other data-driven products in production.
Strong proficiency with AWS cloud services (EC2, S3, SageMaker, Lambda, etc.) and experience using them to scale ML solutions.
Proven experience with ML deployment pipelines and MLOps best practices, including CI/CD, infrastructure-as-code, and workflow orchestration (Docker, Kubernetes, Airflow). Familiarity with monitoring tools to ensure model and system reliability.
Solid Python skills, along with knowledge of common ML and data libraries (pandas, scikit-learn, TensorFlow, PyTorch). Understanding of software engineering fundamentals: version control (Git), testing, and code quality.
Good grasp of machine learning fundamentals and statistics, with the ability to debug models and optimize algorithms for performance. Experience with large-scale datasets (SQL/NoSQL databases or data warehouses) is a plus.
Strong communication and teamwork skills - able to collaborate with data scientists, engineers, and business stakeholders, and explain technical concepts clearly.
English level C1
offered :
Start date: ASAP (dont worry about your notice period)
Initially remote work, later hybrid work 1-2 times a week in the office in Gdańsk
