We are looking for ML engineer that will own the build and maintenance of data and ML pipelines. At the core of a product is invoice digitization to transform invoice data, for example, locked away in PDFs, into a rich and clean digital data asset. And our ideal candidate can make it reality, and also monitor and maintain our products.
Responsibilities:
— Perform inference using existing NLP and computer vision mode
— Use human-in-the-loop annotations to automatically retrain and deploy updated models
— Monitor and maintain the models in production over time
— Refactor code form data scientists to push into production
— Architect and deliver new pipelines to enrich invoice data from our machine learning models
— Make models available as APIs
Requirements:
— 3+ years of Python and SQL
— 2+ years of main machine learning algorithms (classification, regression, prediction)
— Experience with AWS (S3, Lambda, API Gateway, SageMaker, Step Functions)
— Experience with NLP libraries, such as scikit-learn, PySpark, spaCY, NLTK, TextBlob
— Experience with debugging
— Organized with a high attention to detail
— Ensure application performance, uptime, and scale, maintaining high standards of code quality and thoughtful application design
— Good written and verbal communication skills
— Upper Intermediate English level
Additional:
— Experience with СV(Computer Vision) libraries: OpenCV, Tensor, Keras, scikit-image.
— Building ETL/ML pipelines with GCP, AWS, Dataricks etc.
— Working and building APIs
We offer:
— Opportunity to grow as an expert;
— Regular results-based salary review;
— Flexible working conditions;
— 24 days of paid vacation;
— 10 sick days;
— Office in the city center;
— Friendly and open-minded team;
— English classes;
— Relax and fun zones.