Security Data Scientist - CTO Office at Bloomberg in New York, NY

We are the CTO Security Architecture group. We solve complex security problems to enable innovative new products, and prototype the next generation of infrastructure security technologies. Whether we’re designing our next generation security controls, or threat modeling our distributed systems, our goal is to define the future of how we secure Bloomberg’s infrastructure. That’s where you come in.

What’s in it for you:

As a member of the Security Data Science team, you will work with large scale platforms and datasets in order to create purpose-built security models using statistical and machine learning approaches (supervised and unsupervised). The output of the work will be used to improve threat detection and help protect the entire company from malicious activities.

We have a lot of very advanced and fun projects we are working on such as base-lining and anomaly detection with petabyte-scale network data, graph computation, deep learning for malware detection and so much more!

We'll trust you to:

- Take a technical leadership role in defining strategies for machine learning models

- Foster developing technology to make advanced analytics more measurable using industry standard’s methodologies (e.g.: Cyber Killchain, Mitre ATTC&K)

- Help build out our technical product road map and define set the standards for these technologies, working with partners in our CISO's office as well as in Engineering

- Identify visibility gaps and remediate using a risk-driven approach

- Research new approaches to problems and publish your work if interested

You’ll need to have:

- 6+ years of hands-on programming experience in a programming language (Java, Scala, C/C++) and a scripting language (Python)

- 4+ years of experience developing and deploying security-related analytical workloads

- An in-depth understanding of statistics and machine learning techniques both supervised and unsupervised

- Experience with enterprise-grade development and execution environments such as Hadoop, Spark, Druid, Tensorflow, Keras, numpy, etc.

- An ability to multitask and work under pressure

We’d love to see:

Note: The below are not requirements but optional skills that would help accelerate the candidate’s ability to be productive. If the following areas interest you, then you could be a great fit!

- Big Data technologies: Hadoop, Map/Reduce, Spark, Flink, Hive, Druid, etc.

- ML technologies: mllib, NLP, tensorflow, kera, pytorch

- Graph computation: Janusgraph, Neo4j, Tinkerpop, GraphX, etc.

- Networking: TCP/IP, Network traffic capture and analysis

- Security Information and Events Management (SIEM)

- User, Entity and Behavior Analytics (UEBA)

- Search/NoSQL technology: Hbase, ElasticSearch, Solr, Lucene

- RDBMS/SQL: SparkSQL, Postgres, Mariadb, etc.

- Messaging: Kafka, MQ, Pub/Sub, SOAP, REST

- Ability to learn new languages and frameworks and evolve with the team