AI Engineer – Agentic AI

CoreAi Consulting; Phoenix (AZ); On-site; USD 120,000 - 180,000; Full time

Job summary

CoreAi Consulting seeks an experienced AI Engineer with 5+ years of software engineering and 2+ years in building agentic AI apps, LLM-powered solutions, and automation. You will design enterprise AI solutions using Python, LLM frameworks, RAG, and vector databases for scalable workflows across enterprise systems.

The role focuses on deploying GenAI, agent orchestration, and secure APIs, collaborating with product teams, and delivering observability and guardrails in production environments.

Qualifications

• 5+ years of software engineering experience with strong Python programming skills.
• 2+ years of hands-on experience building AI applications using Large Language Models.
• Strong experience with Agentic AI concepts, autonomous agents, AI orchestration, and workflow automation.
• Experience with AI frameworks such as LangGraph, LangChain or similar.
• Experience designing and implementing Retrieval-Augmented Generation (RAG) architectures.
• Experience with embeddings, semantic search, vector databases, and knowledge retrieval systems.
• Experience working with vector databases such as Pinecone, Milvus, Weaviate, Chroma, Redis Vector, FAISS, OpenSearch, or similar.
• Strong experience building REST APIs using FastAPI, Flask, or similar
• Experience integrating AI applications with enterprise systems through REST APIs, GraphQL, messaging platforms, or event-driven architectures.
• Experience with Docker, Kubernetes, Git, GitHub Actions, and CI/CD pipelines.
• Experience deploying cloud-native applications on AWS, Azure, or Google Cloud Platform.
• Strong understanding of distributed systems, microservices, asynchronous programming, and event-driven architectures.
• Experience implementing authentication, authorization, and secure AI application design.
• Strong debugging, performance tuning, and production support experience for AI applications.

Responsibilities

• Design and develop enterprise AI applications using Python and cloud-native architectures.
• Build intelligent AI agents and multi-agent systems capable of reasoning, planning, tool usage, and autonomous task execution.
• Develop GenAI solutions using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), embeddings, and vector databases.
• Design and implement agent orchestration workflows using modern AI frameworks such as LangGraph, LangChain or similar technologies.
• Develop AI-powered assistants, copilots, and workflow automation solutions for enterprise business processes.
• Build and maintain knowledge retrieval systems, embedding pipelines, semantic search, and contextual memory for AI applications.
• Integrate AI agents with enterprise applications, REST APIs, databases, messaging systems, and third-party services.
• Design secure and scalable APIs and microservices to support AI applications and agent workflows.
• Optimize prompt engineering, context management, memory strategies, and tool selection to improve AI response quality.
• Evaluate, benchmark, and integrate commercial and open-source LLMs based on business requirements.
• Implement observability, monitoring, logging, evaluation, and guardrails for production AI systems.
• Collaborate with product managers, architects, and engineering teams to translate business requirements into scalable AI solutions.
• Deploy and manage AI applications on AWS, Azure, or GCP using modern DevOps and CI/CD practices.

Skills

Python programming

LLMs

Agentic AI

REST APIs

CI/CD

Cloud platforms

Distributed systems

Debugging

Observability

Tools

LangGraph

LangChain

Pinecone

Milvus

Weaviate

Chroma

Redis Vector

FAISS

OpenSearch

FastAPI

Flask

GitHub Actions

Job description

We are seeking an experienced AI Engineer with 5+ years of software engineering experience and 2+ years of hands-on expertise in building Agentic AI applications, LLM-powered solutions, and intelligent workflow automation. The ideal candidate will have strong Python development skills and experience designing enterprise AI solutions using modern LLM frameworks, retrieval-augmented generation (RAG), vector databases, and multi-agent architectures.

This role involves designing, developing, and deploying scalable AI applications that automate business processes, integrate with enterprise systems, and leverage autonomous AI agents to improve productivity and decision-making.

Key Responsibilities

• Design and develop enterprise AI applications using Python and cloud-native architectures.
• Build intelligent AI agents and multi-agent systems capable of reasoning, planning, tool usage, and autonomous task execution.
• Develop GenAI solutions using Large Language Models (LLMs), Retrieval-Augmented Generation (RAG), embeddings, and vector databases.
• Design and implement agent orchestration workflows using modern AI frameworks such as LangGraph, LangChain or similar technologies.
• Develop AI-powered assistants, copilots, and workflow automation solutions for enterprise business processes.
• Build and maintain knowledge retrieval systems, embedding pipelines, semantic search, and contextual memory for AI applications.
• Integrate AI agents with enterprise applications, REST APIs, databases, messaging systems, and third-party services.
• Design secure and scalable APIs and microservices to support AI applications and agent workflows.
• Optimize prompt engineering, context management, memory strategies, and tool selection to improve AI response quality.
• Evaluate, benchmark, and integrate commercial and open-source LLMs based on business requirements.
• Implement observability, monitoring, logging, evaluation, and guardrails for production AI systems.
• Collaborate with product managers, architects, and engineering teams to translate business requirements into scalable AI solutions.
• Deploy and manage AI applications on AWS, Azure, or GCP using modern DevOps and CI/CD practices.

Required Qualifications

• 5+ years of software engineering experience with strong Python programming skills.
• 2+ years of hands-on experience building AI applications using Large Language Models
• Strong experience with Agentic AI concepts, autonomous agents, AI orchestration, and workflow automation.
• Experience with AI frameworks such as LangGraph, LangChain or similar.
• Experience designing and implementing Retrieval-Augmented Generation (RAG) architectures.
• Experience with embeddings, semantic search, vector databases, and knowledge retrieval systems.
• Experience working with vector databases such as Pinecone, Milvus, Weaviate, Chroma, Redis Vector, FAISS, OpenSearch, or similar.
• Strong experience building REST APIs using FastAPI, Flask, or similar
• Experience integrating AI applications with enterprise systems through REST APIs, GraphQL, messaging platforms, or event-driven architectures.
• Experience with Docker, Kubernetes, Git, GitHub Actions, and CI/CD pipelines.
• Experience deploying cloud-native applications on AWS, Azure, or Google Cloud Platform.
• Strong understanding of distributed systems, microservices, asynchronous programming, and event-driven architectures.
• Experience implementing authentication, authorization, and secure AI application design.
• Strong debugging, performance tuning, and production support experience for AI applications.

Preferred Qualifications

• Experience with Model Context Protocol (MCP) servers and tool integration.
• Experience with AI evaluation frameworks, observability platforms, and LLM monitoring tools.
• Knowledge of prompt optimization, guardrails, hallucination mitigation, and AI safety best practices.
• Exposure to AI-assisted software development tools such as GitHub Copilot, Cursor, Claude Code, or similar.