AI Platform Engineer

CEI; Dallas, Northern (TX, KY); Hybrid; USD 96,000 - 138,000; Full time

Job summary

CEI is seeking a Senior Agentic AI Developer to design, build, and deploy enterprise-grade AI agents and intelligent automation solutions. This role focuses on agentic AI applications, RAG systems, LLM-powered workflows, and scalable AI platforms using Python and modern AI frameworks.

The ideal candidate has hands-on experience building production AI systems, integrating LLMs, orchestrating multi-agent workflows, and deploying cloud-native applications that support real-world business processes.

Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Data Science, or a related technical field.
• 5+ years of software development experience with strong proficiency in Python.
• Experience building and deploying Generative AI, LLM, or Agentic AI solutions in production environments.
• Experience developing RAG architectures and integrating vector databases.
• Strong understanding of prompt engineering, embeddings, semantic search, and LLM evaluation techniques.
• Experience building APIs and microservices using Python frameworks such as FastAPI.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Experience with containerization and deployment technologies including Docker and Kubernetes.
• Strong troubleshooting, debugging, and problem-solving skills.

Responsibilities

• Design, develop, and deploy agentic AI applications using modern LLM frameworks and orchestration platforms.
• Build Retrieval-Augmented Generation (RAG) solutions leveraging enterprise data sources, vector databases, and semantic search technologies.
• Develop AI agents capable of tool calling, workflow automation, reasoning, and decision support.
• Create scalable APIs and backend services to support AI-enabled products and applications.
• Design and implement document ingestion, knowledge retrieval, embedding generation, and context management pipelines.
• Collaborate with product, engineering, and business teams to identify and deliver AI-driven solutions.
• Evaluate, test, and optimize LLM performance, response quality, latency, and reliability.
• Implement monitoring, observability, security, and governance controls for enterprise AI systems.
• Participate in architecture discussions, proof-of-concept development, and technical design reviews.
• Create and maintain technical documentation, implementation plans, and best practices for AI development.

Skills

Python

AI/ML systems

RAG architectures

LLM integration

APIs / Microservices

Cloud platforms

Docker / Kubernetes

Prompt engineering

LangChain / LangGraph

FastAPI

Vector databases

Education

Bachelor's degree in CS/related

Tools

LangChain

LangGraph

OpenAI

Azure OpenAI

Amazon Bedrock

Docker

Kubernetes

FastAPI

AWS

Azure

GCP

Job description

Back AI Platform Engineer – Other Dallas, TX Contract On-Site Sep 25, 2026

Role

Senior Agentic AI Developer – Remote – EST Hours – $85/hour W2

We are seeking a Senior Agentic AI Developer to design, build, and deploy enterprise-grade AI agents and intelligent automation solutions. This role will focus on developing agentic AI applications, Retrieval-Augmented Generation (RAG) systems, LLM-powered workflows, and scalable AI platforms using Python and modern AI frameworks.

The ideal candidate has hands‑on experience building production AI systems, integrating Large Language Models (LLMs), orchestrating multi‑agent workflows, and deploying cloud-native applications that support real‑world business processes.

Responsibilities

• Design, develop, and deploy agentic AI applications using modern LLM frameworks and orchestration platforms.
• Build Retrieval-Augmented Generation (RAG) solutions leveraging enterprise data sources, vector databases, and semantic search technologies.
• Develop AI agents capable of tool calling, workflow automation, reasoning, and decision support.
• Create scalable APIs and backend services to support AI-enabled products and applications.
• Design and implement document ingestion, knowledge retrieval, embedding generation, and context management pipelines.
• Collaborate with product, engineering, and business teams to identify and deliver AI-driven solutions.
• Evaluate, test, and optimize LLM performance, response quality, latency, and reliability.
• Implement monitoring, observability, security, and governance controls for enterprise AI systems.
• Participate in architecture discussions, proof-of-concept development, and technical design reviews.
• Create and maintain technical documentation, implementation plans, and best practices for AI development.

Required Qualifications

• Bachelor's degree in Computer Science, Software Engineering, Data Science, or a related technical field.
• 5+ years of software development experience with strong proficiency in Python.
• Experience building and deploying Generative AI, LLM, or Agentic AI solutions in production environments.
• Experience developing RAG architectures and integrating vector databases.
• Strong understanding of prompt engineering, embeddings, semantic search, and LLM evaluation techniques.
• Experience building APIs and microservices using Python frameworks such as FastAPI.
• Experience with cloud platforms such as AWS, Azure, or GCP.
• Experience with containerization and deployment technologies including Docker and Kubernetes.
• Strong troubleshooting, debugging, and problem-solving skills.

Preferred Qualifications

• Experience with LangChain, LangGraph, CrewAI, AutoGen, or similar agent orchestration frameworks.
• Experience integrating AI agents with enterprise systems, databases, APIs, and workflow platforms.
• Familiarity with OpenAI, Anthropic, Azure OpenAI, Amazon Bedrock, or other enterprise LLM platforms.
• Experience with MLOps, LLMOps, and AI governance practices.
• Experience developing multi-agent systems and autonomous workflow solutions.
• Exposure to Go or other backend programming languages.

Technical Environment

• Python
• FastAPI
• LangChain / LangGraph
• OpenAI, Claude, Azure OpenAI, Amazon Bedrock
• Retrieval-Augmented Generation (RAG)
• Vector Databases
• Docker & Kubernetes
• AWS / Azure / GCP
• REST APIs & Microservices
• Git, CI/CD Pipelines
• LLMOps & Monitoring Frameworks