Senior LLMOps Engineer: GenAI Infra & RAG Architect

Steampunk, Inc.; McLean (VA); On-site; USD 145,000 - 185,000; Full time

Job summary

Steampunk, Inc. in McLean, VA is seeking an experienced Senior LLMOps Engineer to design, implement, and maintain production-grade LLM pipelines, deployment architectures, and monitoring systems across enterprise environments.

You will build scalable RAG solutions, optimize model hosting, oversee CI/CD for GenAI, ensure governance and security, and mentor engineers while collaborating with Data Scientists and AI Product Engineers.

Qualifications

• Bachelor’s degree or higher and 10+ years total experience.
• 5+ years in software/data engineering or MLOps with 2+ years in LLM/GenAI operations.
• Experience with RAG pipelines and secure GenAI infrastructure.

Responsibilities

• Architect, build, and maintain scalable LLM and RAG pipelines with hosting and retrieval layers.
• Lead secure GenAI infrastructure across cloud environments for reliability and cost efficiency.
• Develop automated evaluation, testing, and governance for LLM outputs.
• Create and maintain Python-based services and automation for LLM/RAG pipelines.
• Mentor junior engineers and collaborate with AI Product Engineers and Data Scientists.

Skills

Python

Hugging Face Transformers

vLLM

TensorRT-LLM

CI/CD

Docker

Kubernetes

LangChain

Vector databases

AWS/Azure/GCP

Education

Bachelor’s degree

Tools

Docker

Kubernetes

Terraform

CloudFormation

FastAPI

PyTorch

Job description

Steampunk, Inc. in McLean, VA is seeking an experienced Senior LLMOps Engineer to design, implement, and maintain production-grade LLM pipelines, deployment architectures, and monitoring systems across enterprise environments.

You will build scalable RAG solutions, optimize model hosting, oversee CI/CD for GenAI, ensure governance and security, and mentor engineers while collaborating with Data Scientists and AI Product Engineers.