Senior GenAI LLMOps Engineer - Secure, Scalable Pipelines

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

Job summary

Steampunk is seeking a Senior LLMOps Engineer in McLean, VA to design, implement, and maintain production-grade LLM pipelines and GenAI infrastructure. You will lead RAG systems, model hosting, and retrieval workflows across cloud environments while ensuring governance and cost efficiency.

You will build automated evaluation, CI/CD for AI workloads, and collaborate with data scientists to productionize prototypes into enterprise-grade solutions. Strong Python and cloud experience are required.

Qualifications

• Ability to obtain and maintain a U.S. government security clearance.
• Bachelor’s degree with 10+ years of total experience.
• 5+ years in software/data/ML ops with 2+ years in LLM/GenAI operations.
• Hands-on experience with RAG pipelines and retrieval systems.
• Fluent Python programming skills.
• Experience deploying models with Transformers and specialized runtimes.
• Proficient in FastAPI, PyTorch, LangChain and vector databases.
• Cloud platforms (AWS/Azure/GCP) and model hosting experience.
• CI/CD for AI workloads and infrastructure-as-code expertise.

Responsibilities

• Architect, build, and maintain scalable LLM and RAG pipelines.
• Design secure GenAI infrastructure across clouds for reliability and cost efficiency.
• Create automated evaluation systems for safety, latency and governance.
• Develop CI/CD workflows for datasets, model lineage, and testing.
• Collaborate with AI Product Engineers to productionize prototypes.
• Integrate vector DBs, model gateways, guards, and retrieval systems.
• Implement observability to track performance, hallucinations, and costs.
• Lead troubleshooting for deployment, inference, and pipeline issues.
• Mentor engineers and contribute to reusable tooling.

Skills

Python

Hugging Face Transformers

vLLM

TensorRT-LLM

LangChain

LlamaIndex

FastAPI

PyTorch

Agile methodologies

Prompt engineering

Education

Bachelor’s degree

10+ years of total experience

Tools

Docker

Kubernetes

Terraform

CloudFormation

FAISS

Milvus

Pinecone

Git

Job description

Steampunk is seeking a Senior LLMOps Engineer in McLean, VA to design, implement, and maintain production-grade LLM pipelines and GenAI infrastructure. You will lead RAG systems, model hosting, and retrieval workflows across cloud environments while ensuring governance and cost efficiency.

You will build automated evaluation, CI/CD for AI workloads, and collaborate with data scientists to productionize prototypes into enterprise-grade solutions. Strong Python and cloud experience are required.