Data Scientist

Overview:

SOSi is seeking a skilled Data Scientist to join our analytics team working on an innovative MLOps workload leveraging cutting-edge technologies and supporting a government customer in Huntsville, Alabama. This role will be responsible for delivering automation to key national security missions interacting with petabyte-scale data on supercomputing resources.

In this role, you will conduct sophisticated data analytics, data mining, exploratory analysis, predictive analysis, and statistical analysis. You will leverage scientific techniques to transform petabyte-scale data into insightful data products to enable data-driven decisions. You will partner with Data Engineers to refactor manual workflows to produce highly automated MLOPs based workloads. You will perform using scrumban techniques and be embedded with end users.

The team will work with technologies including:

• Open source, Commercial, and Government software packages such as Kafka, Beam, NumPy, Kubeflow, Nvidia Triton, PyTorch, TensorFlow, Weaviate, Neo4j, Grafana, etc.
• Cloud native techniques and containerization with Docker
• Infrastructure as Code with Terraform
• Configuration as Code with OPA
• Observability with tools like EFK and LOKI + OTel
• Leverage GitOps patterns and CI/CD with tools like GitLab, Argo, and Harness
• Perform SAST/DAST security with tools like SonarQube
• Perform Kubernetes and K3s orchestration with tools like Rancher and Konvoy

SOSi is seeking data talent to unlock insights from massive datasets supporting strategic national security objectives. If you have a passion for data science and want to apply your skills to impactful projects at scale, we want to hear from you!

Responsibilities:

• Retrieve and process massive structured and unstructured datasets
• Build ML models and automated systems like recommendation and scoring tools
• Perform statistical analysis and data mining to create predictive systems
• Visualize insights using Microsoft Office, Tableau, Python, R
• Develop ML prototype solutions with TensorFlow, PyTorch etc.
• Evaluate model performance by applying data science and math
• Design, develop, and test ML applications using Python, Linux, Docker
• Brief methodology and results to technical and non-technical audiences
• Collaborate with teams to share best practices and domain knowledge

Qualifications:

• Active TS/SCI Security Clearance
• At least 4 years experience as a Data Scientist or advanced analytical role
• Expertise in Python, R, SQL, statistics, data mining
• Knowledge of ML and deep learning techniques
• Ability to communicate complex insights

Preferred Qualifications:

• Knowledge of SciML
• Experience with MLOps
• Experience with Petabyte scale data sets
• Experience with large-scale, multi-INT analytics
• BS or MS in Computer Science, Statistics, Mathematics, Physics or a quantitative field

Working Conditions:

• Working conditions are normal for an office environment.
• Fast paced, deadline-oriented environment.
• May require periods of non-traditional working hours including consecutive nights or weekends (if applicable).