Senior AI/ML Engineer: Lead LLM Systems & RAG Pipelines

Vizient; Centennial (CO); On-site; USD 102,000 - 179,000; Full time

Job summary

Vizient is seeking an AI/ML engineer to design, build, and deploy scalable ML and LLM-based solutions that deliver measurable business impact. You will own the full AI lifecycle from experimentation to production, including RAG pipelines, embeddings, and agentic workflows.

You will collaborate across teams to translate complex problems into reliable, high‑performing systems while advancing governance, monitoring, and cost optimization.

Qualifications

• Advanced degree preferred in CS/Engineering/Data Science.
• 5+ years of relevant experience.
• Experience deploying ML models to production.
• Experience building LLM-powered applications such as RAG systems.
• Strong Python and production‑grade software practices.
• Experience with model serving frameworks and API development (e.g., FastAPI, MLflow).
• Experience with vector databases and embedding workflows.
• Familiarity with LangChain/LlamaIndex and related tools.
• CI/CD pipelines, containerization, and cloud deployment experience.
• Experience in startup, high-growth, or large-scale enterprise environments.

Responsibilities

• Lead design, development, and deployment of ML models and LLM-based applications.
• Translate business challenges into scalable AI solutions and define success metrics.
• Design and implement RAG pipelines, embedding strategies, and vector search architectures.
• Build agentic workflows, prompt strategies, and orchestration patterns for LLM systems.
• Own AI/ML solutions end to end from scoping to deployment and operations.
• Evaluate model/LLM performance using automated and human-in-the-loop methods.
• Optimize AI systems for latency, cost, scalability, and reliability.
• Maintain scalable deployment strategies, CI/CD pipelines, and MLOps workflows.
• Implement monitoring, drift detection, retraining pipelines, and lifecycle management.
• Design and maintain production-grade data pipelines with validation and lineage.

Skills

Python

ML engineering

Production‑grade software engineering

Regulated environments familiarity

Startup/high-growth experience

Education

Advanced degree preferred in Computer Science / Engineering / Data Science

Tools

FastAPI

MLflow

LangChain

LlamaIndex

Vector databases

Embedding workflows

CI/CD pipelines

Containerization

Cloud deployment

Job description

Vizient is seeking an AI/ML engineer to design, build, and deploy scalable ML and LLM-based solutions that deliver measurable business impact. You will own the full AI lifecycle from experimentation to production, including RAG pipelines, embeddings, and agentic workflows.

You will collaborate across teams to translate complex problems into reliable, high‑performing systems while advancing governance, monitoring, and cost optimization.