ML Deployment Engineer - Production Pipelines & CI/CD

Erias Ventures; Maryland; Hybrid; USD 232,000 - 255,000; Full time

Benefits offered by this job

Above Market Pay

401k with immediate vesting

Bonuses for business development

Professional development support

Company paid health insurance

Job summary

Erias Ventures is seeking an ML Deployment Engineer in the United States to move models from research to production inference services that run in Kubernetes or similar environments. You will work with a small research/SDK team and end users to align development with real‑world needs.

The role requires 14+ years SWE experience, a TS/SCI clearance with polygraph, and a Bachelor’s degree in CS; partial telework is available and you will help deploy robust, scalable ML pipelines.

Qualifications

• Must have strong Python experience and DevOps/CI‑CD expertise.
• Experience taking projects from prototype to production.
• Excellent communication for technical and non‑technical audiences.
• Self‑motivated with the ability to work both independently and collaboratively.

Responsibilities

• Collaborate with end users and researchers to understand requirements.
• Build CI/CD and packaging around Python on NVIDIA Triton Inference Server with TensorRT.
• Tune pipelines for throughput and support deployment transitions.
• Review and test software components against design requirements.
• Create user documentation and deployment best practices.
• Contribute to system design, including infrastructure-as-code and hardware/software trade-offs.

Skills

Python

CI/CD

Production deployment

Communication

Self-motivation

Education

Bachelor's degree in Computer Science or related discipline

Tools

Docker

Kubernetes

TensorRT

ONNX

CUDA

NVIDIA Triton Inference Server

Job description

Erias Ventures is seeking an ML Deployment Engineer in the United States to move models from research to production inference services that run in Kubernetes or similar environments. You will work with a small research/SDK team and end users to align development with real‑world needs.

The role requires 14+ years SWE experience, a TS/SCI clearance with polygraph, and a Bachelor’s degree in CS; partial telework is available and you will help deploy robust, scalable ML pipelines.