Production ML Engineer - Pipelines, Deployment & AWS

Sperry Rail; Shelton (CT); On-site; USD 120,000 - 190,000; Full time

Job summary

Sperry Rail is building a US data science team to turn research into scalable systems. You will deploy models and data pipelines on AWS, ensure reproducibility, and own production workflows from data ingestion to inference.

The role emphasizes building robust, observable systems on top of cloud platforms, with collaboration across US and UK teams to leverage rail inspection data. You will shape the data and model lifecycle end-to-end.

Qualifications

• Proficient in Python and scientific stack; deploy ML analyses to production.
• Experience putting ML models or analytics into production and maintaining runs.
• Build data pipelines handling structured/unstructured data at scale.
• Strong SQL and knowledge of relational/non-relational databases.
• Experience with AWS cloud services and cloud-native architecture.
• Containerization (Docker) and infrastructure-as-code.
• Understand software engineering practices: testing, quality, design patterns.
• Familiar with Git, CI/CD and Agile development.

Responsibilities

• Take prototypes to production and own them
• Build and maintain data pipelines feeding models from large rail inspection data sources
• Implement data/model versioning to trace results to code and data
• Monitor models for drift and data quality, implement retraining paths
• Build APIs and services delivering model outputs to users/systems
• Design compute/orchestration for training/inference on AWS
• Set engineering standards: testing, reviews, environments, CI/CD
• Collaborate with cloud and UK teams on shared data sources
• Automate handoffs between ideas and running models
• Write clean, well-documented code and participate in reviews/planning
• Document architecture decisions and runbooks

Skills

Python

ML production

Data pipelines

SQL

AWS

Docker

CI/CD

Git

Agile

Communication

Education

Bachelor’s degree in CS/Engineering

Tools

Docker

AWS

SageMaker

Airflow

Git

Job description

Sperry Rail is building a US data science team to turn research into scalable systems. You will deploy models and data pipelines on AWS, ensure reproducibility, and own production workflows from data ingestion to inference.

The role emphasizes building robust, observable systems on top of cloud platforms, with collaboration across US and UK teams to leverage rail inspection data. You will shape the data and model lifecycle end-to-end.