Data Scientist / ML Engineer (Antarctica Capital)

EarthDaily is seeking a highly skilled Data Scientist / Machine Learning Engineer to design, build, deploy, and maintain scalable machine learning systems within Antarctica Capital. The role involves collaborating on existing neural network models and improving performance across various machine learning activities within the firm.

Responsibilities:

• Refactor Neural Network
• Collaborate with architect and author of neural network bond risk product to identify areas for improvement
• Lead architecture and development effort
• Contribute to the design, development, and deployment of firm-wide architecture, norms, policies, infrastructure and methodologies for machine learning activities across multiple company groups
• Design, develop, and deploy machine learning models into production environments
• Collaborate with data scientists to translate prototypes into production-ready systems
• Build and maintain data pipelines, feature stores, and model-serving infrastructure
• Evaluate and optimize model performance, latency, and scalability
• Implement automated training, testing, and deployment workflows (MLOps)
• Monitor models in production and address issues related to drift, performance degradation, or data quality
• Conduct code reviews and ensure best practices in ML engineering and software development
• Stay current with emerging ML/AI technologies and recommend tools or frameworks that improve team efficiency
• Other Duties as Assigned

Requirements:

• 7+ years building machine learning models with Python and AWS
• Hands-on experience with ML frameworks such as Pytorch and TensorFlow
• Experience with ML observability and training platforms/technologies like ML Flow
• Proficiency in building and deploying models using cloud platforms such as AWS (e.g. in Fargate)
• Solid understanding of algorithms, data structures, and software engineering principles
• Tensorflow, Pytorch
• Python, Pydantic
• AWS Lambda, Fargate, Step Functions, other usual suspects
• IaC / CDK
• Experience with data and compute orchestration tools like AWS Step Functions or Apache Airflow
• Exposure to large scale data warehousing and query engine technologies like Iceberg and Athena, and to columnar data storage formats like parquet
• Experience working with and modernizing legacy software, including migrating from on-prem to cloud-based deployments
• API development with FastAPI