Senior LLMOps Engineer: Scale GenAI Pipelines & RAG

Steampunk; Bloomington (IL); On-site; USD 145,000 - 185,000; Full time

Job summary

Steampunk is seeking an experienced Senior LLMOps Engineer to design, implement, and maintain production-grade LLM and RAG pipelines across enterprise environments. You will build hosting, inference, retrieval, and context management, with a focus on security, reliability, and governance.

The role requires expert Python, hands-on experience with Hugging Face Transformers, vLLM, and vector databases, plus CI/CD for AI workloads.

Qualifications

• U.S. government security clearance capability is required or achievable.
• Bachelor’s degree with 10+ years total experience.
• 5+ years in software/data engineering, MLOps, or cloud engineering with 2+ years on LLM/GenAI ops.
• Hands-on RAG pipeline design, build and maintenance experience.
• Fluency in Python and production-grade model deployment experience.

Responsibilities

• Architect and maintain scalable LLM and RAG pipelines with hosting, inference, and context management.
• Design secure GenAI infrastructure across cloud environments for reliability and cost efficiency.
• Build automated evaluation systems for quality, safety, latency and governance compliance.
• Develop CI/CD workflows for AI applications including dataset versioning and model lineage.
• Collaborate with AI Product Engineers to productionize prototypes into enterprise-grade systems.
• Integrate vector databases, model gateways, content filters, and guardrails end-to-end.
• Implement observability to track performance, hallucinations, costs, and usage patterns.
• Lead troubleshooting and RCA for deployment and inference issues.
• Produce Python-based services and integrations to support LLM/RAG pipelines.
• Stay current with MLSecOps trends and governance practices.

Skills

Security clearance

Software engineering

MLOps

LLM/GenAI operations

RAG pipelines

Python

CI/CD for AI/ML

Observability & monitoring

Technical leadership

Cloud architectures

Docker & Kubernetes

Terraform/CloudFormation

AI governance & safety

Agile project mgmt

Education

Bachelor’s degree

Tools

Hugging Face Transformers

vLLM

TensorRT-LLM

LangChain

LlamaIndex

FAISS

Milvus

Pinecone

FastAPI

PyTorch

Job description

Steampunk is seeking an experienced Senior LLMOps Engineer to design, implement, and maintain production-grade LLM and RAG pipelines across enterprise environments. You will build hosting, inference, retrieval, and context management, with a focus on security, reliability, and governance.

The role requires expert Python, hands-on experience with Hugging Face Transformers, vLLM, and vector databases, plus CI/CD for AI workloads.