PLATA is looking for an Applied Research Engineer to join the Risks Team and create state-of-the-art foundational deep learning models for fintech.

The team works with Python, PyTorch, MLFlow, AWS, Snowflake, Claude Code, OpenAI Codex and Cursor.

Challenges that await you:

• Train self-supervised models on discrete sequences to beat the state of the art and achieve business impact in downstream tasks across PLATA, including credit risk, transaction anti-fraud and LTV forecasting.
• Stay up to date with the latest research and apply modern NLP and deep learning techniques to fintech models.
• Work with large multimodal datasets, including tabular, behavioral and transactional data, as well as device and network information, text, time series and graphs.
• Optimize compute resources for both model training and inference.
• Own solutions end-to-end, from the initial idea and data collection to experiments, training, inference optimization and impact evaluation.
• Perform rigorous evaluations.
• Write articles and speak at industry conferences.

What makes you a great fit:

• Strong theoretical knowledge of machine learning, deep learning and NLP.
• Demonstrated experience developing and training modern deep learning models.
• Experience with dataset design and data mixing for deep learning training.
• Understanding of how to use compute resources efficiently and run experiments to validate research ideas.
• Strong communication skills.
• High autonomy and ownership.

Bonus skills:

• PhD, publications or previous research experience.
• Experience training transformer models with 1B+ parameters.
• Experience with transformer architectures for non-natural-language event sequences, such as CoLES, BERT4Rec or SASRec.
• Experience training self-supervised, embedding or ranking models.
• Experience in fintech or banking.
• English level B1 or higher for communication with an international team.

What PLATA offers:

• Relocation support to Cyprus, Serbia, Spain, Georgia or Kazakhstan, including assistance for the employee and their family.
• Flexible work from one of PLATA’s offices or remotely within GMT-2 to GMT+5.
• Healthcare coverage.
• Education budget for language lessons, professional training and certifications.
• Wellness budget for mental health and fitness activities.
• 20 days of annual leave and paid sick leave.