ML Deployment Engineer - TS/SCI

Wyetech; Laurel (MD); Hybrid; USD 88,000 - 165,000; Full time

Benefits offered by this job

SEP IRA 20%

200 hours PTO

Medical plan + HSA

Vision and Dental

Life and AD&D

Disability

Hospital Indemnity

Identity Theft Protection

Employee Referral Bonus up to $10,000

Mobility among contracts

Team events

Two branded clothing orders

Job summary

Wyetech, LLC seeks an ML Deployment Engineer to move video, image, speech, and text analytics from research to production inference services. You will work in Kubernetes or similar environments, collaborating with end users and researchers to align development with real-world needs.

You will build CI/CD around Python on NVIDIA Triton, tune pipelines for throughput, and create deployment documentation while supporting customer transitions. Active TS/SCI clearance is required.

Qualifications

• TS/SCI with agency appropriate polygraph.
• Bachelor's Degree in Computer Science or related discipline.
• 14+ years of software engineering experience.
• Four (4) years of additional software development experience on comparable projects may be substituted for a bachelor’s degree.

Responsibilities

• Build the CI/CD and packaging around Python on NVIDIA Triton Inference Server, with TensorRT execution providers and BLS in-service pipelines.
• Tune pipelines for throughput and support them through customer transition.
• Review and test software components against design requirements.
• Create comprehensive user documentation and deploy best practices.

Skills

Python

CI/CD

Docker

Kubernetes

Production deployment

Communication

Independence

Education

Bachelor's degree in Computer Science

Tools

NVIDIA Triton Inference Server

TensorRT

Job description

Wyetech, LLC seeks an ML Deployment Engineer to move video, image, speech, and text analytics from research to production inference services. You will work in Kubernetes or similar environments, collaborating with end users and researchers to align development with real-world needs.

You will build CI/CD around Python on NVIDIA Triton, tune pipelines for throughput, and create deployment documentation while supporting customer transitions. Active TS/SCI clearance is required.