AVP/VP - Big Data Solution Architecture - BFSI

AVP/VP

- Assist APAC team lead with and peers from the Data Innovation Office and Compliance Operations & Technology teams with the implementation, maintenance, and operations of the ADAP solutions. Implement robust data ingestion, indexing and Cloud Online Analytical Processing (COLAP) representations, and interrogate the data using advance algorithm development, and represent the information in visually compelling user interfaces.

- Support an analytics team in the APAC Compliance department, responsible for:

- Providing advanced data ingestion and enrichment techniques, and data-drive interrogation approaches that identify and mitigate AML and Sanctions risk,

- Developing anticipatory intelligence and advanced analytics solutions that proactively identifies risk,

- Providing input to, and creating innovative ideas for performing risk assessments, profiling large transaction volumes at the macro level, and identifying outliers and unusual anomalies in the data for deep dive reviews,

- Developing robust, efficient, and repeatable processes for ensuring high risk customers and transactions are identified, and providing a traceable audit trail to support compliance actions, and informing future requirements to continuously improve the accuracy and effectiveness of ADAP analytics,

- Undertaking techniques such as correlating, clustering, segmentation and predictive analytics to drive and enhance the analytics engine and risk management process,

- Deploying entity extract, enrichments, and analytics on both structured, semi-structured, and unstructured data,

- Continuously improving the AML team's operation performance by producing and analyzing performance metrics,

- Working with senior management based in Hong Kong, and the global AML and Compliance teams, to establish best practices, standardize analytics development and delivery, and engage stakeholders to ensure buy-in and user adoption.

Development Value :

Job Specification :

Experience : Skills :

Key Requirements :

- 3+ years of specific experience in Big Data solution architecture, design, deployment, and implementation. Experience installing, configuring, and maintaining Big Data stack based on open source products (e.g. Top-Level Apache projects: Hadoop, Accumulo, Ambari, ZooKeeper, Kafka, Storm, Spark)

- 3+ years of designing and implementing ETL processes, specifically performing ETL on multiple data sources: structured, semi structure and unstructured data.

- 3+ years designing and implementing custom data ingestion processes to include entity extraction leveraging NLP (StanfordNLP) libraries. Implementing complimentary NLP techniques via custom extraction to further enrich extracted results and gazetteer based on temporal and spatial attributes.

- 2+ years developing analytics to interrogate data for anomaly detection and pattern/typology recognition from both structured and unstructured data.

- 2+ years of experience implementing data-driven analysis, algorithms, and analytics for AML typologies in a Big Data environment, including the development of custom MapReduce and Spark jobs to execute classification, clustering, entity resolution, and data cube generation.

Big Data Software Architecture Development :

- Acts as a data scientist supporting the ADAP technical lead, global stakeholders and Citi O&T.

- The individual will also be highly engaged in the design of the platform's technical - stack- and focus on the design methodology of the platform's functionality, including hands on development (for the deployment, maintenance/operations, and implementation of typology analytics).

- Efforts will include design and implementation of the ADAP platform based on typology review and derived system use cases, with flexibility to adjust to emergent and changing typology characteristics over time.

- The candidate will also support O&T with the installation of stack via traditional means and emerging tools- primarily Zoo Keeper and Ambari.

- The individual must be able to configure and maintain cloud operability as well as support system updates.

Data Ingestion and Systems Integration :

- Candidate must possess extensive experience using current ETL and ingestion technologies such as Storm to support big data's volume, velocity, and variety.

- The individual must have experience in ingesting data from multiple sources handling various formats and types, and writing custom ingestion jobs for entity extraction, enrichment, temporal and spatial indexing, and COLAP storage.

- This includes ongoing manual programming as necessary, and assessment, refinement, and tuning of ingestion data ontology, NLP implementation and performance tuning.

- [Data Ingestion] Candidate should also possess a strong understanding of SOAP- and RESTful web service construction to provide external systems with API's to consume data and feedback, and to integrate with various user interface visualizations and partnering systems. [Systems Integration]

Data Science and Advance Analytics :

- Candidate possesses deep understanding and practice implementation experience with natural language processing libraries (e.g. StanfordNLP), search and optimization, neural networks, and control theory (ex. Benfords law, fuzzy logic, Bayesian belief networks). Experience includes implementation of analytics across massive BigTable implementation (tera- to petabytes), combined with the experience implementing Money Laundering techniques at scale.

- The data scientist will construct relevant algorithms from AML typology variables to build models that will be leveraged for various number of analytic algorithms.

- These models can be used for traditional supervised and unsupervised classification techniques. In addition these models can be used to identify trends and trend prediction.

- The team lead will also be responsible for capturing performance accuracy of all algorithms calculating accuracy and precision.

Visualization and Reporting :

- Experience generating wireframes or mockups for UI/UX developers to build dashboards as well as design and integration with REST and SOAP services to interact with custom data access APIs for data retrieval

Qualifications : Competencies :

- BS in Computer Science, Applied Statistics, Operations Research, Mathematics, Physics, or equivalent.

- MS preferred

- 3+ years of progressive Big Data development, specifically in the areas of machine learning, deep learning, and natural language processing.

Programming Languages (Subject Matter Expert Competency) : Java, C++, C#, Python, Scala, HTML5

Big Data Frameworks (Subject Matter Expert Competency) : Hadoop, YARN, MapReduce, Accumulo, SPARK, Kafka, Storm, HBase, Zookeeper, Ambari, Puppet

Analysis Packages (Advanced Competency) : R, SAS, SPASS, MatLab

Domain (Advanced-Level Competency) : AML typology development and implementation.