AI Agent Developer

Codinix Consulting Services; Minneapolis (MN); On-site; USD 100,000 - 130,000; Full time

Job summary

Codinix Consulting Services is seeking an experienced AI Agent Developer in Minneapolis, MN. This role involves designing and building autonomous AI agents to enhance engineering workflows using large language models (LLMs). Candidates should have over 5 years of software engineering experience and proficiency in Python. The position is on-site 4 days a week and emphasizes collaboration with engineering and security teams to deliver secure AI solutions.

Qualifications

• 5+ years of software engineering experience, with strong proficiency in backend or full-stack development.
• Hands-on experience building applications using LLMs, generative AI, or agent-based systems.
• Strong programming skills in Python (preferred), Java, or similar languages.
• Experience with LLM frameworks such as LangChain, LlamaIndex, or similar.
• Understanding of prompt engineering, tool/function calling, embeddings, and retrieval-augmented generation.

Responsibilities

• Design, develop, and deploy autonomous AI agents using LLMs and agentic frameworks.
• Build AI-powered developer productivity tools for code generation and documentation.
• Integrate leading LLM platforms into enterprise development ecosystems.
• Monitor agent performance and iterate on models for improvements.

Skills

Software engineering experience

Building applications using LLMs

Programming in Python

LLM frameworks (LangChain, LlamaIndex)

API integration and cloud platforms

Tools

Docker

Kubernetes

Job description

Location: Minneapolis, MN (On-site 4 days/week)
Employment Type: Contract

Job Overview

We are seeking an experienced AI Agent Developer to design, build, and scale autonomous and semi-autonomous AI agents that enhance software engineering, DevSecOps, and enterprise developer workflows. This role focuses on leveraging modern large language models (LLMs) and agentic architectures to deliver intelligent automation, improve developer productivity, and streamline engineering operations across the enterprise.

Key Responsibilities

• Design, develop, and deploy autonomous and semi-autonomous AI agents using LLMs and agentic frameworks to solve complex engineering and operational challenges.
• Build AI-powered developer productivity tools, including assistants for code generation, code review, refactoring, debugging, and documentation.
• Develop agents that automate and optimize software engineering workflows such as coding, testing, CI/CD pipelines, DevSecOps processes, and quality assurance.
• Integrate leading LLM platforms and copilots (e.g., GitHub Copilot, Anthropic Claude, OpenAI Codex) into enterprise development ecosystems and toolchains.
• Architect and implement agent orchestration systems, including tool calling, memory management, reasoning loops, and feedback mechanisms to ensure reliability, scalability, and security.
• Collaborate closely with platform engineering, security, and software development teams to deliver secure, compliant, and production-ready AI solutions.
• Continuously evaluate and adopt emerging LLM technologies, frameworks, and agentic design patterns to drive innovation and best practices.
• Monitor agent performance and iterate on models, prompts, and architectures to improve accuracy, efficiency, and user experience.

Required Qualifications

• 5+ years of software engineering experience, with strong proficiency in backend or full-stack development.
• Hands-on experience building applications using LLMs, generative AI, or agent-based systems.
• Strong programming skills in Python (preferred), Java, or similar languages.
• Experience with LLM frameworks such as LangChain, LlamaIndex, Semantic Kernel, or similar.
• Understanding of prompt engineering, tool/function calling, embeddings, vector databases, and retrieval-augmented generation (RAG).
• Experience integrating APIs and working with cloud platforms (AWS, Azure, or GCP).
• Familiarity with DevSecOps practices, CI/CD pipelines, and modern software delivery workflows.
• Strong understanding of software engineering principles, system design, and scalable architecture.

Preferred Qualifications

• Experience building production-grade AI agents or copilots in enterprise environments.
• Familiarity with GitHub Copilot, OpenAI, Anthropic, or similar LLM ecosystems.
• Knowledge of security, compliance, and governance considerations for AI systems.
• Experience with containerization and orchestration tools (Docker, Kubernetes).
• Exposure to multi-agent systems or reinforcement learning concepts is a plus.

Soft Skills

• Strong problem-solving and systems thinking abilities
• Ability to work cross-functionally with engineering and security teams
• Strong communication skills, especially in translating AI concepts to business stakeholders
• Self-driven with the ability to thrive in a fast-paced contract environment