Applied AI Engineer

Stellent IT LLC; Broomfield (CO); Hybrid; USD 96,000 - 165,000; Full time

Job summary

Stellent IT LLC in Colorado is seeking an Applied AI Engineer with 7–12 years of experience to design, build, and deploy enterprise-grade AI solutions in a Microsoft Azure environment.

You will work on generative AI, LLM-based apps, RAG systems, and ensure secure, scalable AI integration with PostgreSQL, Service Bus, and Event Hubs, collaborating with cloud and platform teams.

Qualifications

• 7-10 years of software engineering or data science experience with Python and ML frameworks.
• Strong expertise in generative AI, LLMs, embeddings, and vector databases.
• Hands-on experience with Microsoft Azure services (Azure OpenAI, Azure AI Services, Service Bus, Event Hubs, PostgreSQL).

Responsibilities

• Design, build, evaluate, and deploy AI-enabled solutions using Python, PyTorch, TensorFlow, and scikit-learn.
• Deploy ML models with emphasis on accuracy, latency, and cost optimization.
• Develop generative AI and LLM-based apps including AI agents and RAG systems.
• Ensure secure agentic AI with guardrails, validation, retries, and human oversight.
• Collaborate with cloud/platform teams to productionize AI with MLOps and LLMOps.

Skills

Python

LLM applications

Generative AI

Embeddings

Vector databases

Agentic AI

Azure

MLOps

LLMOps

CI/CD

REST APIs

Microservices

PostgreSQL

SQL

Tools

Azure OpenAI

Azure AI Services

Azure Service Bus

Event Hubs

PostgreSQL

Job description

Title: Applied AI Engineer

Location: Broomfield, CO ( Hybrid)

Job Type ; W2 Contract

Experience Range: 7-12 years

Job Description:

Our client is seeking an Applied AI Engineer with 7 10 years of experience to design, build, and deploy enterprise-grade AI solutions, including generative AI and LLM-based applications, within a Microsoft Azure environment.

Responsibilities & Qualifications:

• Design, build, evaluate, and deploy AI-enabled solutions for business-critical applications using Python, PyTorch, TensorFlow, and scikit-learn
• Develop and deploy machine learning models with strong emphasis on model evaluation for accuracy, reliability, hallucination mitigation, latency, and cost optimization
• Build generative AI and LLM-based applications, including AI agents and Retrieval-Augmented Generation (RAG) systems with prompt engineering expertise
• Design secure agentic AI solutions that interact safely with enterprise systems, incorporating guardrails, validation, retries, approval workflows, and human oversight
• Integrate AI solutions with enterprise APIs, databases (PostgreSQL), and Azure messaging systems (Service Bus, Event Hubs)
• Collaborate with cloud and platform engineering teams to productionize AI solutions, implementing MLOps and LLMOps best practices
• Translate operational problems into practical, enterprise-integrated AI solutions aligned with business objectives

Requirements:

• 7 10 years of software engineering or data science experience with demonstrated expertise in Python and machine learning frameworks
• Strong proficiency in generative AI, LLM applications, embeddings, vector databases, and agentic AI solutions
• Hands-on experience with Microsoft Azure services: Azure OpenAI, Azure AI Services, Azure API Management, Azure Service Bus, Event Hubs, PostgreSQL, Entra ID, Key Vault, Monitor, and Application Insights
• Advanced knowledge of machine learning operations (MLOps, LLMOps), CI/CD pipelines, REST APIs, and microservices architecture
• Expert-level SQL and database design with PostgreSQL experience
• Fluent English proficiency for technical communication and cross-team collaboration
• Portfolio or proven track record demonstrating end-to-end AI solution delivery in enterprise environments