Our partner is a well reputed software development center, part of one of the world’s largest banking groups. The Romanian development teams are at the core of the digital transformation journey, working across multiple initiatives, products and technologies, shaping the future of the banking world.

As a Data Scientist, you'll be part of a big data team that develops anti-fraud detection solutions and models, supporting the bank to prevent and manage risks. 

The technology stack you'll be using counts, among others: Python, Hadoop Ecosystem - Spark (Spark SQL, Dataframes, PySpark), HDFS, Hive, YARN, Kerberos, etc.  

This role best fits those candidates who have strong problem solving skills, work well in a team and have preferably been exposed to the financial services industry. 

Your key responsibilities will be to:

• Conceptualize and design ML models to reduce false positive alerts using a combination of Python and big data processing tehcniques (PySpark); 

• Improve existing monitoring framework by identifying new data patterns, use of natural language processing techniques or by implementing anomaly detection models;

• Understand and translate business requirements into technical concepts: run experiments, research and implement appropriate ML algorithms and tools to solve them or to gain new insights into available data;

• Develop relevant visualizations, either as part of exploratory data analysis or to show results using relevant libraries and/or BI tools such as Tableau;

• Ensure that the results of the models are robust, comparable and maintainable over time;

• Monitor performance of the models in production - ensure no degradation occurs below established metrics and retrain when needed;

• Work with Data Engineers to deploy and maintain models in production or to analyze/build data pipelines for new data sources.

• Help create a culture of learning and continuous improvement within your team and beyond.

To thrive in this role, you’ll have:

• Hands on experience with Machine Learning modelling and techniques;

• In depth knowledge of mathematics, statistics and algorithms;

• Ability to write robust code in Python. Knowledge of frameworks for data processing, data wrangling, data visualizations and machine learning modelling - Pandas, NumPy, TensorFlow, Scikit-learn;

• Experience with training, evaluation and deployment of ML models;

• Ideally, you have experience working with Hadoop Ecosystem and technologies such as Spark, Hive, etc; 

• Experience with PySpark or other relevant big data modelling libraries is a plus.

• Fluent in English.

Your benefits:

• Meal vouchers

• Annual Bonuses

• Medical subscriptions

• Life insurance

• Hybrid work – 3 days WFH. Offices are based in Pipera, close to the Metro station – the coolest offices in town

• Extra days off

If you feel you still need to fill some gaps for this position, don't give up - let's talk first.

If interested: send your resume/Linkedin profile to recruitment@itworx.ro and we'll reach out to you shortly.

Else: you can refer an interested friend or acquaintance.

We are committed to promoting equal opportunities in employment, to not only adhere to current employment law, but to harness the full potential of staff and ensure that all individuals are treated fairly and with respect. To meet this aim, we endeavour to treat all job applicants equally, on the basis of merit, competence and ability to do the job. Everybody will be treated equally regardless of race, color, age, religion or belief, gender, gender identity, gender expression, marital or civil partner status, ethnic or national origin, physical or mental disability, sexual orientation, and pregnancy or maternity status (“Protected Characteristics”).