Senior ML Engineer - MLOps for Real-Time Border Detection

Leidos Inc; Vista (CA); On-site; USD 107,900 - 195,050; Full time

Job summary

Leidos is seeking a Senior Machine Learning Engineer to join the Security Enterprise Solutions group. The role focuses on MLOps for object detection and related AI products used to safeguard ports and borders worldwide.

You will own the full ML lifecycle, from data preparation to deployment and monitoring, and collaborate with diverse teams to deliver reliable, scalable models. Travel up to 25% is expected.

Qualifications

• MS or PhD in a data science, engineering, or applied science field with 10+ years of industry experience.
• Full ML lifecycle experience from data prep and training to deployment and monitoring.
• Experience tracking experiments and model performance with MLflow for transparency and auditability.
• Experience with data versioning tools like DVC, MLFlow Dataset, or LakeFs.
• Production ML deployment using Docker or Kubernetes.
• Familiarity with cloud platforms and modern data stacks and MLOps concepts.
• Ability to evaluate approaches and guide technical decisions; strong delivery track record.
• Excellent written and verbal communication; travel up to 25%.

Responsibilities

• Develop, train, and evaluate ML models using modern MLOps practices.
• Design reproducible training pipelines for scalable experimentation.
• Collaborate with cross-functional teams to integrate models into production systems.
• Optimize model performance and reliability through monitoring and iteration.

Skills

ML lifecycle

Experiment tracking

Model deployment

Cloud platforms

Docker/Kubernetes

Cross-functional

Communication

Travel

Education

MS/PhD in Data Science or related field

Tools

Kubeflow

Airflow

MLflow

DVC

LakeFs

Docker

Kubernetes

Job description

Leidos is seeking a Senior Machine Learning Engineer to join the Security Enterprise Solutions group. The role focuses on MLOps for object detection and related AI products used to safeguard ports and borders worldwide.

You will own the full ML lifecycle, from data preparation to deployment and monitoring, and collaborate with diverse teams to deliver reliable, scalable models. Travel up to 25% is expected.