Senior AI Engineer - Agentic AI & LLM Applications

The successful candidate will have experience building, deploying, evaluating, and improving AI applications that interact with real-world data, tools, and users, while being able to clearly explain what they built, how it works, and why it was designed that way. Ideal Candidate: This role is ideal for a software-oriented AI professional who combines strong Python development skills with experience building agentic AI applications, LLM-powered workflows, and production-grade AI systems.

Kforce has a client that is seeking a Senior AI Engineer - Agentic AI & LLM Applications in Greenwood Village, CO. Summary: We're seeking a Senior AI Engineer to design, build, deploy, and evaluate AI agents that leverage large language models, enterprise data, and external tools to automate complex investigations, generate recommendations, and support operational decision-making. This role sits at the intersection of Software Engineering, Agentic AI, Data Science, and Generative AI. This is not a traditional machine learning modeling position. The primary focus is building and maintaining AI-powered applications and agent workflows that consume model outputs, investigate issues, and deliver actionable insights to end users. Responsibilities:

• Design and build AI agents using LangGraph or similar agent frameworks
• Develop agent workflows leveraging LLMs, retrieval, tool calling, memory, and orchestration patterns
• Parse and structure JSON, API, and model outputs for use within agent workflows
• Build applications that integrate multiple data sources and external tools into a unified user experience
• Design agent workflows that balance LLM flexibility with deterministic behavior, reliability, and explainability
• Create evaluation frameworks and benchmark datasets to measure agent accuracy, quality, and performance
• Improve agent quality through prompt engineering, context engineering, observability, and testing
• Deploy and maintain production AI applications using modern CI/CD practices
• Work within and contribute to complex existing Python codebases
• Partner with Data Science, Engineering, Platform, and Business teams to deliver scalable AI capabilities

Requirements:

• 5+ years of experience in AI Engineering, Data Science, Machine Learning, Software Engineering, or a related field
• Strong Python software development experience
• Experience building AI agents or LLM-powered applications
• Hands-on experience with LangGraph or comparable agent frameworks
• Experience with agent orchestration, context management, memory, and tool-calling patterns
• Experience with prompt engineering, retrieval, embeddings, RAG, and LLM-powered workflows
• Strong SQL and structured data experience
• Experience deploying and supporting applications in production environments
• Experience working within and contributing to shared or existing codebases
• Ability to clearly explain technical decisions, architecture, and personal contributions

Preferred Qualifications:

• AWS experience
• LangSmith or agent observability platforms
• Splunk or telemetry/log analytics experience
• CI/CD and production deployment experience
• Experience integrating AI applications with APIs and external systems
• Bash or scripting experience
• Scala exposure
• Spark or distributed computing experience
• Telecommunications, networking, observability, or operational analytics experience
• AWS Bedrock experience

Ideal Candidate: This role is ideal for a software-oriented AI professional who combines strong Python development skills with experience building agentic AI applications, LLM-powered workflows, and production-grade AI systems. The successful candidate will have experience building, deploying, evaluating, and improving AI applications that interact with real-world data, tools, and users, while being able to clearly explain what they built, how it works, and why it was designed that way.