Senior LLMOps Engineer: GenAI Infra & Pipelines Lead

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

Job summary

Steampunk, Inc. in McLean, VA seeks an experienced Senior LLMOps Engineer to design, deploy, and maintain production‑grade LLM pipelines and GenAI infrastructure for enterprise workloads.

You will optimize inference, implement CI/CD for AI models, manage vector databases, and ensure security, governance, and observability across cloud environments.

Collaborate with AI Product Engineers and Data Scientists to productionize prototypes, monitor performance, reduce latency, and control costs.

Qualifications

• Bachelor’s, Master’s, or Ph.D. in Computer Science, ML, Data Engineering, or related field.

Responsibilities

• Architect and maintain scalable LLM and RAG pipelines with model hosting, inference optimization, retrieval layers, and context management frameworks.
• Lead secure GenAI infrastructure design across cloud environments for reliability, performance, and cost efficiency.
• Build automated evaluation systems to assess LLM output quality, safety, latency, and governance adherence.
• Develop CI/CD workflows for LLM-based apps, including dataset versioning, model lineage, and automated testing of prompts and model behaviors.
• Collaborate with AI Product Engineers and Data Scientists to productionize prototypes into enterprise-grade systems.
• Integrate vector databases, model gateways, content filters, and guardrail frameworks into end-to-end LLM solutions.
• Implement observability and monitoring for performance, hallucinations, cost, and user interaction patterns.
• Lead root-cause analysis for deployment, inference, or pipeline issues.
• Stay current with LLM architectures, inference optimizations, fine-tuning, and MLSecOps patterns.
• Ensure data privacy, ethical AI, and AI governance throughout pipelines.
• Mentor junior engineers and contribute to Steampunk’s AI engineering best practices.
• Contribute to growth of AI & Data Exploitation Practice.

Education

Bachelor’s, Master’s, or Ph.D. in Computer Science, Machine Learning, Data Engineering, or a related field

Tools

Hugging Face Transformers

vLLM

TensorRT-LLM

Python

FastAPI

PyTorch

LangChain

LlamaIndex

vector databases

FAISS

Milvus

Pinecone

Docker

Kubernetes

Terraform

CloudFormation

Airflow

Job description

Steampunk, Inc. in McLean, VA seeks an experienced Senior LLMOps Engineer to design, deploy, and maintain production‑grade LLM pipelines and GenAI infrastructure for enterprise workloads.

You will optimize inference, implement CI/CD for AI models, manage vector databases, and ensure security, governance, and observability across cloud environments.

Collaborate with AI Product Engineers and Data Scientists to productionize prototypes, monitor performance, reduce latency, and control costs.