Python - AI Engineer Contractor

Omm IT Solutions•Dallas, TX

5h•Onsite

About The Position

We are seeking an experienced AI Engineer to design, build, and deploy production-grade GenAI solutions. This role focuses on developing agentic AI systems, GraphRAG applications, and enterprise LLM services that solve real business problems. The ideal candidate has hands-on experience taking GenAI applications from proof of concept into production, enjoys working with modern agent development frameworks, and stays current with the rapidly evolving GenAI ecosystem.

Requirements

Bachelor's degree in Computer Science or a related technical field (or equivalent practical experience).
5+ years of software engineering experience, including recent experience building GenAI or LLM-powered applications.
Demonstrated experience taking GenAI applications from proof of concept into production.
Hands-on experience with one or more modern agent development frameworks such as Google ADK, LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar.
Strong Python development skills, including FastAPI and REST API design.
Experience implementing RAG or GraphRAG solutions using embeddings, vector databases, knowledge graphs, and enterprise data sources.
Experience deploying AI workloads using Docker and AWS, Azure, or GCP.
Strong communication, collaboration, and problem-solving skills.

Nice To Haves

Familiarity with LLMOps practices including CI/CD, prompt management, model/version governance, monitoring, and evaluation.
Experience with LLM evaluation tools such as LangSmith, Ragas, DeepEval, or equivalent frameworks.
Demonstrated curiosity and commitment to staying current with the rapidly evolving GenAI and agentic AI landscape.

Responsibilities

Design, build, and deploy production-grade GenAI applications leveraging foundation models and advanced architectures such as GraphRAG.
Develop autonomous AI agents using modern agent development frameworks such as Google ADK, LangGraph, CrewAI, AutoGen, Semantic Kernel, or similar technologies.
Take AI solutions from prototype through production deployment, ensuring scalability, reliability, observability, and maintainability.
Design and implement advanced RAG and GraphRAG pipelines that integrate enterprise knowledge sources using embeddings and knowledge graphs.
Build scalable REST APIs using Python (FastAPI) that power LLM-driven enterprise applications.
Containerize and deploy AI services using Docker and cloud platforms including AWS, Azure, or GCP.
Implement LLM evaluation frameworks using LangSmith, Ragas, DeepEval, or custom evaluation pipelines to measure answer quality, groundedness, latency, and hallucination rates.
Apply LLMOps best practices including CI/CD, prompt/version management, automated testing, monitoring, and production observability.
Collaborate with engineering teams to integrate AI capabilities into enterprise platforms.
Mentor engineers and contribute to technical best practices for GenAI application development.
Stay current with emerging GenAI technologies, agent frameworks, and industry best practices, evaluating new tools and approaches as the ecosystem evolves.