> Markdown version of [/jobs/ext/4743649-ai-software-engineer](https://www.wearedevelopers.com/jobs/ext/4743649-ai-software-engineer). Every page supports `.md` or `Accept: text/markdown`. Links point to the HTML versions so they work for humans too. Agent guide: [/agents.md](https://www.wearedevelopers.com/agents.md). --- # AI Software Engineer - **Company:** Grant Thornton - **Location:** Chicago, IL, United States - **Experience:** Expert - **Contract:** Permanent contract - **Skills:** LangGraph Framework, Agile Methodology, Artificial Intelligence, Microsoft Azure, Memory Management, Python (Programming Language), Machine Learning, Oop Languages, Azure Machine Learning, Software Engineering, AI Infrastructure, Microsoft Agent Framework, Pytorch, Retrieval-Augmented Generation, Delivery Pipeline, Large Language Models, Multi-Agent Systems, Prompt Engineering, Deep Learning, Model Validation, Generative AI, Agentic-AI, Scikit Learn, Low Latency, CrewAI, Machine Learning Operations, Claude, Azure AI, Google Gemini, Model Context Protocol, GPT, Agent2Agent Protocol - **Published:** November 16, 2026 - **Apply:** https://www.careerbuilder.com/job-details/ai-software-engineer-chicago-il--df993ac9-8259-4eb2-8523-29f0fc4dad3f ## About the Role Software Engineering, Artificial Intelligence (AI), Twitter, LinkedIn, Facebook, Artificial Intelligence (AI), Establish Priorities, Agile Programming Methodologies, Customer Experience, Professional Services, * 5+ years of hands-on experience in ML/DL projects, of which 2+ years building and delivering GenAI/LLM applications in production. * Proven experience designing and deploying agentic AI systems: multi-agent orchestration, tool calling, agent memory and state management, and agent evaluation. * Hands-on experience with the Azure AI ecosystem, ideally Azure AI Foundry and Azure Machine Learning. * Expertise in LLM development, prompt engineering, vector-based retrieval, and RAG evaluation. * Solid grounding in classical ML and deep learning (e.g., scikit-learn, PyTorch); time-series forecasting or anomaly detection experience is a strong plus. * Strong command of Python with solid OOP principles, and experience with MLOps/LLMOps practices. * Familiarity with Responsible AI concepts: fairness, transparency, AI governance, and hallucination mitigation. * Effective communication with technical and non-technical audiences; strong problem-solving skills. * A collaborative, self-motivated mindset with the ability to drive projects with minimal supervision. Bonus Qualifications: * Experience with IBM watsonx (watsonx.ai, watsonx Orchestrate, watsonx.governance) and IBM Granite models. * Experience with agent interoperability standards (MCP, A2A) in production settings. * Experience with real-time AI systems or low-latency inference. * Relevant certifications in Azure AI or machine learning (e.g., AI-102). ## Description We are looking for a Senior AI/ML Engineer to join our AI Center of Excellence. You'll design, build, and deploy state-of-the-art Generative and Agentic AI solutions, from LLM-powered applications to autonomous multi-agent systems, primarily on the Microsoft Azure AI stack (Azure AI Foundry). You'll also bring solid ML fundamentals, applying classical techniques such as time-series forecasting and anomaly detection where they're the right tool, and collaborate with cross-functional teams to deliver secure, scalable AI systems built on Responsible AI practices. The key responsibilities of this role will include: * Design, build, and deploy production-grade agentic AI systems, multi-agent workflows, tool-using agents, and orchestration pipelines, using frameworks such as LangGraph, CrewAI, and the Microsoft Agent Framework, primarily on Azure AI Foundry. * Design robust GenAI architectures: RAG and agentic RAG pipelines, memory management, prompt engineering, and tool integration via the Model Context Protocol (MCP). * Work with modern foundation models (GPT, Claude, Gemini, Llama, Mistral), including fine-tuning with domain-specific datasets. * Develop classical ML solutions where appropriate, especially time-series forecasting and anomaly detection, and integrate them into agentic workflows as callable tools. * Build automated pipelines for agent and model evaluation, observability, guardrails, and Responsible AI compliance. * Write clean, scalable Python code applying strong OOP principles, and produce clear technical documentation. * Provide technical leadership, mentor junior engineers, and help shape our AI strategy.