Rail ML Engineer: Production-Grade Models

Sperry Rail, Inc.; Shelton (CT); On-site; USD 120,000 - 180,000; Full time

Job summary

Sperry Rail, Inc. is seeking a Machine Learning Engineer to join our US data science team in Shelton, CT.

You will turn prototype models into production-grade systems, building scalable data pipelines, versioning data and models, and deploying on AWS with SageMaker and related tools. You will own end-to-end model lifecycle, monitor for drift, and collaborate with cloud and UK teams to ensure robust, reproducible results across rail inspection data.

Qualifications

• Strong proficiency in Python and the scientific stack.
• Experience putting machine learning models into production and keeping them running.
• Experience building data pipelines and working with structured and unstructured data at scale.
• SQL and relational/non-relational databases.
• Experience with AWS cloud services and cloud-native architecture.
• Containerization (Docker) and infrastructure-as-code.
• Software engineering principles: testing, code quality, patterns.
• Version control (Git), CI/CD, and agile practices.
• Strong problem-solving and quick learning abilities.
• Good communication to explain technical concepts to non-technical stakeholders.
• Bachelor's degree in CS/engineering or related fields.
• ML tooling and workflow orchestration: MLflow, SageMaker Pipelines, Kubeflow, etc.
• Observability and monitoring tooling familiarity.

Responsibilities

• Take models and analyses from prototype to production, owning them thereafter.
• Build and maintain data pipelines feeding models across large-scale rail inspection data.
• Implement model and data versioning to trace results to code and data.
• Monitor deployed models for drift, degradation, and data quality; design retraining paths.
• Build and maintain APIs/services delivering model outputs to users and systems.
• Design compute/orchestration for training/inference on AWS (S3, Lambda, Glue, SageMaker).
• Set engineering standards: testing, code review, environments, CI/CD, release practices.
• Coordinate with cloud engineering and UK teams on data sources and platform.
• Automate manual steps between ideas and running models.
• Write clean, tested, well-documented code following best practices.
• Participate in code reviews, sprint planning, and technical design discussions.
• Document architecture decisions, runbooks, and operational procedures.

Skills

Python

ML in production

Data pipelines

SQL

AWS

Docker

Git

CI/CD

Agile

Communication

Education

Bachelor's degree in computer science, engineering, or a related technical field

Tools

MLflow

SageMaker

Kubeflow

Airflow

Dagster

Step Functions

CloudWatch

Grafana

Job description

Sperry Rail, Inc. is seeking a Machine Learning Engineer to join our US data science team in Shelton, CT.

You will turn prototype models into production-grade systems, building scalable data pipelines, versioning data and models, and deploying on AWS with SageMaker and related tools. You will own end-to-end model lifecycle, monitor for drift, and collaborate with cloud and UK teams to ensure robust, reproducible results across rail inspection data.