Posted Jan 22, 2018 - Requisition No. 64621
We are part of a new startup within Bloomberg that leverages financial expertise, cutting edge technologies, and innovation to solve critical problems for the world's leading financial institutions and corporations. Our engineers focus on helping clients address regulatory and operational challenges arising from KYC (Know Your Customer) and AML (Anti Money Laundering). We build a portfolio of rapidly increasing web-based products and APIs that facilitate secure document exchange and permissioning (Entity Exchange), screening peps, sanctions and adverse media (Entity Intelligence), and data cleansing and verification (Entity Verification).
On the KYC Machine Learning team, you will play a critical role in the development of these products. We focus on building industrial-scale models pertaining to the areas of natural language processing (NLP), text understanding, entity resolution, classification, pattern recognition, recommendation, and ranking, using a diverse array of data-sets in the financial and regulatory ecosystems.
Our customers use this information in making crucial decisions; it is paramount that our systems have high precision, accuracy, and low latency. As a member of this team, you will tackle a very interesting set of computational problems such as search and retrieval, document classification, sentiment analysis, document summarization, recommendation, named entity recognition (NER) and disambiguation (NED).
Identify and formulate various challenges in AML and KYC domains as Machine Learning (ML) problems.
Design, develop, and validate proposed ML solutions.
Deploy these solutions on a large scale where performance and maintainability are critical.
Stay abreast of latest advances and best practices in academia and industry.
Contribute to research communities through open source projects or by publishing papers at top-tier conferences.
2+ years of industry experience in IR (Information Retrieval) / ML / Recommendation Systems / NLP domain.
2+ years of experience programming in C++, Java, Python, or Scala.
PhD or Master’s degree in IR / ML / NLP domain or Bachelor’s degree with at least 5+ years of relevant work experience.
Publications in top-tier conferences such as NIPS, ICML, ACL, EMNLP, KDD, etc.
Experience with deep learning tools like TensorFlow, PyTorch, Keras.
Experience with Big data technologies such as Spark and Hadoop.
Understanding of AML or KYC.